2 variantsCheck my PC
AI model catalog
225 open-weights models you can run locally, with estimated memory requirements. Size and quantization describe the selected technical default, which can be a base or embedding build. Check any of them against your own computer.
225 models
IBM30M
granite-embedding
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serv…
F16Apache License
2 variantsCheck my PC
Ollama Library137M
nomic-embed-text
A high-performing open embedding model with a large token context window.
2K contextF16Apache License
1 variantCheck my PC
Ollama Library270M
functiongemma
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
32K contextQ8_0Gemma Terms of Use
2 variantsCheck my PC
Ollama Library278M
paraphrase-multilingual
Sentence-transformers model that can be used for tasks like clustering or semantic search.
F16Apache License
1 variantCheck my PC
Ollama Library300M
embeddinggemma
EmbeddingGemma is a 300M parameter embedding model from Google.
2K contextQ4_0Gemma Terms of Use
3 variantsCheck my PC
Ollama Library335M
mxbai-embed-large
State-of-the-art large embedding model from mixedbread.ai
F16Apache License
1 variantCheck my PC
Ollama Library22M
snowflake-arctic-embed
A suite of text embedding models by Snowflake, optimized for performance.
F16Apache License
5 variantsCheck my PC
1 variantCheck my PC
Ollama Library567M
bge-m3
BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
8K contextF16MIT License
1 variantCheck my PC
Ollama Library568M
snowflake-arctic-embed2
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
8K contextF16
1 variantCheck my PC
Ollama Library1.0B
minicpm-v4.6
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
256K contextMultimodalQ4_K_M
1 variantCheck my PC
DeepSeek AI1.3B
deepseek-coder
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
16K contextQ4_K_MDEEPSEEK LICENSE AGREEMENT
36 variantsCheck my PC
Ollama Library1.8B
moondream
moondream2 is a small vision language model designed to run efficiently on edge devices.
2K contextMultimodalQ4_K_MApache License
6 variantsCheck my PC
Ollama Library1.1B
tinydolphin
An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
4K contextQ4_K_MApache License
6 variantsCheck my PC
Ollama Library1.1B
tinyllama
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
2K contextQ4_K_M
12 variantsCheck my PC
Ollama Library1.2B
lfm2.5-thinking
LFM2.5 is a new family of hybrid models designed for on-device deployment.
125K contextQ4_K_MLICENSE TEXT
2 variantsCheck my PC
IBM1.0B
granite3-moe
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
4K contextQ4_K_MApache License
12 variantsCheck my PC
Ollama Library500M
reader-lm
A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.
250K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International
12 variantsCheck my PC
Hugging Face135M
smollm
🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.
2K contextQ4_K_MApache License
36 variantsCheck my PC
Hugging Face135M
smollm2
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
8K contextQ4_K_MApache License
18 variantsCheck my PC
Ollama Library1.5B
deepscaler
A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular ma…
128K contextQ4_K_MMIT License
3 variantsCheck my PC
Stability AI1.6B
stablelm2
Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Po…
4K contextQ4_K_MSTABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT
30 variantsCheck my PC
IBM2.0B
granite3-guardian
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
8K contextQ8_0Apache License
6 variantsCheck my PC
IBM2.0B
granite3.2-vision
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from ta…
16K contextMultimodalQ4_K_MApache License
3 variantsCheck my PC
IBM2.0B
granite3-dense
The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code…
4K contextQ4_K_MApache License
12 variantsCheck my PC
Ollama Library2.7B
dolphin-phi
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
2K contextQ4_K_MMICROSOFT RESEARCH LICENSE TERMS
5 variantsCheck my PC
Ollama Library7.0B
orca-mini
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
2K contextQ4_K_M
45 variantsCheck my PC
Microsoft2.7B
phi
Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
2K contextQ4_K_MMIT License
6 variantsCheck my PC
Stability AI3.0B
stable-code
Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.
16K contextQ4_K_MSTABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT
12 variantsCheck my PC
Stability AI3.0B
stablelm-zephyr
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
4K contextQ4_K_MSTABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
Hugging Face1.0B
starcoder
StarCoder is a code generation model trained on 80+ programming languages.
8K contextQ4_K_M
36 variantsCheck my PC
Hugging Face3.0B
starcoder2
StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
16K contextQ4_K_MBigCode Open RAIL-M v1 License Agreement
24 variantsCheck my PC
Meta AI1.0B
llama3.2
Meta's Llama 3.2 goes small with 1B and 3B models.
128K contextQ4_K_MLLAMA 3.2 COMMUNITY LICENSE AGREEMENT
24 variantsCheck my PC
DeepSeek AI3.0B
deepseek-ocr
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
8K contextMultimodalF16MIT License
1 variantCheck my PC
IBM1.0B
granite3.1-moe
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
128K contextQ4_K_MApache License
12 variantsCheck my PC
IBM3.0B
granite4
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
128K contextQ4_K_MApache License
5 variantsCheck my PC
Ollama Library3.0B
smallthinker
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
32K contextQ4_K_MQwen RESEARCH LICENSE AGREEMENT
3 variantsCheck my PC
IBM3.0B
granite-code
A family of open foundation models by IBM for Code Intelligence
2K contextQ4_K_MApache License
58 variantsCheck my PC
Ollama Library3.8B
nuextract
A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.
4K contextQ4_K_MApache License
6 variantsCheck my PC
Microsoft3.8B
phi3
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
4K contextQ4_K_MMicrosoft.
24 variantsCheck my PC
Microsoft3.8B
phi3.5
A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
4K contextQ4_K_MMIT License
6 variantsCheck my PC
Microsoft3.8B
phi4-mini
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is…
128K contextQ4_K_MMicrosoft.
3 variantsCheck my PC
Microsoft3.8B
phi4-mini-reasoning
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
128K contextQ4_K_MMicrosoft.
3 variantsCheck my PC
MicrosoftBuild size unknown
Phi-3 Mini
Microsoft's Phi-3 Mini — compact 3.8B model with strong reasoning. Supports up to 128K context.
Q4_K_MMIT
1 variantCheck my PC
Google DeepMind1.0B
gemma3
The current, most capable model that runs on a single GPU.
32K contextMultimodalQ4_K_MGemma Terms of Use
14 variantsCheck my PC
Ollama Library3.8B
llava-phi3
A new small LLaVA model fine-tuned from Phi 3 Mini.
4K contextMultimodalQ4_K_M
2 variantsCheck my PC
Alibaba Cloud500M
qwen
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
32K contextQ4_K_MTongyi Qianwen RESEARCH LICENSE AGREEMENT
140 variantsCheck my PC
NVIDIA4.0B
nemotron-mini
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
4K contextQ4_K_MNVIDIA AI Foundation Models Community License Agreement
6 variantsCheck my PC
Ollama Library4.0B
tev1
A 4B decision model from Together AI for fast classification.
256K contextQ4_K_MApache License
3 variantsCheck my PC
Ollama Library4.0B
medgemma
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
128K contextMultimodalQ4_K_MHealth AI Developer Foundations Terms of Use
4 variantsCheck my PC
Ollama Library4.0B
medgemma1.5
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
128K contextMultimodalQ4_K_MHealth AI Developer Foundations Terms of Use
2 variantsCheck my PC
Ollama Library4.0B
translategemma
A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
128K contextMultimodalQ4_K_MGemma Terms of Use
6 variantsCheck my PC
63 variantsCheck my PC
Google DeepMindBuild size unknown
gemma3n
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
32K contextQ4_K_MGemma Terms of Use
6 variantsCheck my PC
Ollama Library7.0B
bakllava
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
32K contextMultimodalQ4_K_M
6 variantsCheck my PC
Meta AI7.0B
codellama
A large language model that can use text prompts to generate and discuss code.
16K contextQ4_K_MLLAMA 2 COMMUNITY LICENSE AGREEMENT
71 variantsCheck my PC
DeepSeek AI7.0B
deepseek-llm
An advanced language model crafted with 2 trillion bilingual tokens.
4K contextQ4_K_M
21 variantsCheck my PC
Ollama Library7.0B
dolphin-mistral
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
32K contextQ4_K_MApache License
42 variantsCheck my PC
Ollama Library7.0B
dolphincoder
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
16K contextQ4_K_MBigCode Open RAIL-M v1 License Agreement
12 variantsCheck my PC
Ollama Library7.0B
duckdb-nsql
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
16K contextQ4_K_M
6 variantsCheck my PC
TII7.0B
falcon
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
2K contextQ4_0FALCON 180B TII LICENSE VERSION 1.0
14 variantsCheck my PC
Meta AI7.0B
llama2
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
4K contextQ4_K_MLLAMA 2 COMMUNITY LICENSE AGREEMENT
36 variantsCheck my PC
Meta AI7.0B
llama2-chinese
Llama 2 based model fine tuned to improve Chinese dialogue ability.
4K contextQ4_K_M
12 variantsCheck my PC
Meta AI7.0B
llama2-uncensored
Uncensored Llama 2 model by George Sung and Jarrad Hope.
2K contextQ4_K_MLLAMA 2 COMMUNITY LICENSE AGREEMENT
11 variantsCheck my PC
Ollama Library7.0B
llava
🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language under…
4K contextMultimodalQ4_K_MApache License
36 variantsCheck my PC
Ollama Library7.0B
magicoder
🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs w…
16K contextQ4_K_M
6 variantsCheck my PC
Ollama Library7.0B
meditron
Open-source medical large language model adapted from Llama 2 to the medical domain.
2K contextQ4_K_M
7 variantsCheck my PC
Ollama Library7.0B
medllama2
Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
4K contextQ4_K_M
6 variantsCheck my PC
Mistral AI7.0B
mistral-openorca
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
32K contextQ4_K_M
6 variantsCheck my PC
Mistral AI7.0B
mistrallite
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
32K contextQ4_K_M
6 variantsCheck my PC
Ollama Library7.0B
neural-chat
A fine-tuned model based on Mistral with good coverage of domain and language.
32K contextQ4_K_M
18 variantsCheck my PC
Ollama Library7.0B
notus
A 7B chat model fine-tuned with high-quality data and based on Zephyr.
32K contextQ4_K_MMIT License
6 variantsCheck my PC
Ollama Library7.0B
nous-hermes
General use models based on Llama and Llama 2 from Nous Research.
4K contextQ4_K_M
23 variantsCheck my PC
Ollama Library7.0B
openchat
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
8K contextQ4_K_MApache License
18 variantsCheck my PC
Ollama Library7.0B
openhermes
OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
32K contextQ4_K_M
12 variantsCheck my PC
Ollama Library7.0B
orca2
Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoni…
4K contextQ4_K_MMICROSOFT RESEARCH LICENSE TERMS
12 variantsCheck my PC
Ollama Library7.0B
samantha-mistral
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
32K contextQ4_K_M
18 variantsCheck my PC
Ollama Library7.0B
sqlcoder
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
32K contextQ4_K_MCreative Commons Attribution-ShareAlike 4.0 International
18 variantsCheck my PC
Stability AI7.0B
stable-beluga
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
4K contextQ4_K_MSTABLE BELUGA NON-COMMERCIAL COMMUNITY LICENSE AGREEMENT
18 variantsCheck my PC
Ollama Library7.0B
starling-lm
Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
8K contextQ4_K_MApache License
12 variantsCheck my PC
Ollama Library7.0B
vicuna
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
2K contextQ4_K_M
42 variantsCheck my PC
Ollama Library7.0B
wizard-math
Model focused on math and logic problems
2K contextQ4_K_MMICROSOFT RESEARCH LICENSE TERMS
24 variantsCheck my PC
Ollama Library7.0B
wizard-vicuna-uncensored
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
2K contextQ4_K_M
18 variantsCheck my PC
Ollama Library7.0B
wizardcoder
State-of-the-art code generation model
16K contextQ4_K_MMICROSOFT RESEARCH LICENSE TERMS
24 variantsCheck my PC
Ollama Library7.0B
wizardlm2
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
32K contextQ4_K_MApache License
9 variantsCheck my PC
Ollama Library7.0B
xwinlm
Conversational model based on Llama 2 that performs competitively on various benchmarks.
4K contextQ4_K_M
29 variantsCheck my PC
Ollama Library7.0B
yarn-llama2
An extension of Llama 2 that supports a context of up to 128k tokens.
64K contextQ4_K_M
24 variantsCheck my PC
Ollama Library7.0B
yarn-mistral
An extension of Mistral to support context windows of 64K or 128K.
32K contextQ4_K_M
11 variantsCheck my PC
Ollama Library7.0B
zephyr
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
32K contextQ4_K_MMIT License
15 variantsCheck my PC
Ollama Library7.0B
mathstral
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
32K contextQ4_K_MApache License
6 variantsCheck my PC
Mistral AI7.0B
mistral
The 7B model released by Mistral AI, updated to version 0.3.
16K contextQ4_K_MApache License
30 variantsCheck my PC
Alibaba Cloud7.0B
codeqwen
CodeQwen1.5 is a large language model pretrained on a large amount of code data.
64K contextQ4_K_M../../../Qwen/CodeQwen1.5-7B-Chat/LICENSE
9 variantsCheck my PC
Allen Institute for AI7.0B
olmo-3
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and p…
64K contextQ4_K_MApache License
9 variantsCheck my PC
Allen Institute for AI7.0B
olmo2
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open mod…
4K contextQ4_K_MApache License
6 variantsCheck my PC
TII1.0B
falcon3
A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
8K contextQ4_K_MFalcon 3 TII Falcon License
12 variantsCheck my PC
Google DeepMindBuild size unknown
gemma4
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and mu…
128K contextMultimodalQ4_K_MApache License
11 variantsCheck my PC
Ollama Library7.0B
marco-o1
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
32K contextQ4_K_MApache License
3 variantsCheck my PC
Ollama Library8.0B
minicpm-v
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
32K contextMultimodalQ4_K_MVersion 1.0, June 5, 2024
6 variantsCheck my PC
Ollama Library7.0B
openthinker
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
32K contextQ4_K_MApache License
12 variantsCheck my PC
Alibaba Cloud500M
qwen2
Qwen2 is a new series of large language models from Alibaba group
32K contextQ4_K_MApache License
33 variantsCheck my PC
Alibaba Cloud1.5B
qwen2-math
Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities o…
4K contextQ4_K_MApache License
18 variantsCheck my PC
Alibaba Cloud500M
qwen2.5
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens an…
32K contextQ4_K_MApache License
45 variantsCheck my PC
Alibaba Cloud500M
qwen2.5-coder
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
32K contextQ4_K_MApache License
72 variantsCheck my PC
Alibaba Cloud4.0B
qwen3-embedding
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
40K contextQ4_K_M
8 variantsCheck my PC
Ollama Library7.0B
bespoke-minicheck
A state-of-the-art fact-checking model developed by Bespoke Labs.
32K contextQ4_K_M
6 variantsCheck my PC
Shanghai AI Laboratory1.8B
internlm2
InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.
32K contextQ4_K_MApache License
24 variantsCheck my PC
LG AI Research2.4B
exaone-deep
EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters devel…
32K contextQ4_K_MEXAONE AI Model License Agreement 1.1 - NC
9 variantsCheck my PC
LG AI Research2.4B
exaone3.5
EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and r…
32K contextQ4_K_MEXAONE AI Model License Agreement 1.1 - NC
9 variantsCheck my PC
Ollama Library1.5B
opencoder
OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.
4K contextQ4_K_MVersion Release Date: July 16, 2024
6 variantsCheck my PC
Cohere8.0B
aya
Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
8K contextF16Creative Commons Attribution-NonCommercial 4.0 International Public
10 variantsCheck my PC
Cohere8.0B
aya-expanse
Cohere For AI's language models trained to perform well across 23 different languages.
8K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International Public
12 variantsCheck my PC
Ollama Library3.0B
cogito
Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including co…
128K contextQ4_K_MLLAMA 3.2 COMMUNITY LICENSE AGREEMENT
14 variantsCheck my PC
Cohere7.0B
command-r7b
The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge…
8K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International Public
3 variantsCheck my PC
Cohere7.0B
command-r7b-arabic
A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middl…
16K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International Public
3 variantsCheck my PC
Ollama Library8.0B
dolphin-llama3
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skil…
250K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT
18 variantsCheck my PC
Ollama Library8.0B
dolphin3
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local m…
128K contextQ4_K_MLLAMA 3.1 COMMUNITY LICENSE AGREEMENT
3 variantsCheck my PC
Ollama Library3.0B
hermes3
Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research
128K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT
24 variantsCheck my PC
Meta AI1.0B
llama-guard3
Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.
128K contextQ4_K_MLLAMA 3.1 COMMUNITY LICENSE AGREEMENT
12 variantsCheck my PC
Meta AI8.0B
llama-pro
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programmin…
4K contextQ4_K_M
12 variantsCheck my PC
Meta AI8.0B
llama3
Meta Llama 3: The most capable openly available LLM to date
8K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT
24 variantsCheck my PC
Meta AI8.0B
llama3-chatqa
A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
8K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT
12 variantsCheck my PC
Meta AI8.0B
llama3-gradient
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
1024K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT
12 variantsCheck my PC
Meta AI8.0B
llama3-groq-tool-use
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
8K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT – Adapted For Groq 8B/70B Tool Use
12 variantsCheck my PC
Meta AI8.0B
llama3.1
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
128K contextQ4_K_MLLAMA 3.1 COMMUNITY LICENSE AGREEMENT
36 variantsCheck my PC
Ollama Library8.0B
llava-llama3
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
8K contextMultimodalQ4_K_M
2 variantsCheck my PC
Allen Institute for AI8.0B
tulu3
Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
128K contextQ4_K_MLLAMA 3.1 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
DeepSeek AI1.5B
deepseek-r1
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
128K contextQ4_K_MMIT License
27 variantsCheck my PC
IBM2.0B
granite3.1-dense
The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over thei…
128K contextQ4_K_MApache License
12 variantsCheck my PC
IBM2.0B
granite3.2
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
128K contextQ4_K_MApache License
6 variantsCheck my PC
IBM2.0B
granite3.3
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capab…
128K contextQ4_K_MApache License
2 variantsCheck my PC
Ollama Library8.0B
minicpm-v4.5
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
40K contextMultimodalQ4_K_M
1 variantCheck my PC
Alibaba Cloud600M
qwen3
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
40K contextQ4_K_MApache License
41 variantsCheck my PC
Alibaba Cloud3.0B
qwen2.5vl
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
125K contextMultimodalQ4_K_MApache License
12 variantsCheck my PC
Ollama Library8.0B
rnj-1
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on pa…
32K contextQ4_K_MApache License
3 variantsCheck my PC
IBM8.0B
granite4.1-guardian
Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm…
128K contextQ4_K_MApache License
5 variantsCheck my PC
Ollama Library8.0B
lfm2.5
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
125K contextQ4_K_MLFM Open License v1.0
2 variantsCheck my PC
Ollama Library1.0B
sailor2
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
32K contextQ4_K_M
9 variantsCheck my PC
IBM3.0B
granite4.2
IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented gener…
128K contextQ4_K_MApache License
15 variantsCheck my PC
Alibaba Cloud2.0B
qwen3-vl
The most powerful vision-language model in the Qwen model family to date.
256K contextMultimodalQ4_K_MApache License
24 variantsCheck my PC
01.AI1.5B
yi-coder
Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.
128K contextQ4_K_MApache License
24 variantsCheck my PC
Mistral AI3.0B
ministral-3
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
256K contextMultimodalQ4_K_MApache License
9 variantsCheck my PC
Google DeepMind2.0B
codegemma
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code ge…
8K contextQ4_K_MGemma Terms of Use
30 variantsCheck my PC
Google DeepMind2.0B
gemma
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
8K contextQ4_K_MGemma Terms of Use
36 variantsCheck my PC
Ollama Library9.0B
nimble
A 9B decision model from Bespoke Labs for fast, typed classification.
256K contextQ4_K_MApache License 2.0
2 variantsCheck my PC
Ollama Library9.0B
nimble-v3
A 9B decision model from Bespoke Labs for fast classification, routing, and scoring.
32K contextQ4_K_MBespoke-Nimble-9B-v3 by Bespoke Labs (Shreyas Pimpalgaonkar, Sid Devic, Mrinal Kumar, Pratik Dalal, and Mahesh Sathiamoo
2 variantsCheck my PC
Ollama Library9.0B
ornith
A self-improving family of open-source models for agentic coding
256K contextQ4_K_MMIT License
4 variantsCheck my PC
Alibaba Cloud2.0B
qwen3.5
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
256K contextMultimodalQ4_K_MApache License
12 variantsCheck my PC
Ollama Library9.0B
clef-flash
Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions.
256K contextMultimodalQ8_0Apache License
1 variantCheck my PC
Google DeepMind2.0B
gemma2
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
8K contextQ4_K_MGemma Terms of Use
36 variantsCheck my PC
Google DeepMind2.0B
shieldgemma
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safe…
8K contextQ4_K_MGemma Terms of Use
18 variantsCheck my PC
Zhipu AI9.0B
codegeex4
A versatile model for AI software development scenarios, including code completion.
128K contextQ4_K_MThe glm-4-9b License
6 variantsCheck my PC
Zhipu AI9.0B
glm4
A strong multi-lingual general language model with competitive performance to Llama 3.
8K contextQ4_K_MThe glm-4-9b License
12 variantsCheck my PC
Meta AI11.0B
llama3.2-vision
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
128K contextMultimodalQ4_K_M**Llama 3.2** **Acceptable Use Policy**
6 variantsCheck my PC
TII11.0B
falcon2
Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
2K contextQ4_K_MFalcon 2 11B TII License Version 1.0
6 variantsCheck my PC
Ollama Library10.7B
nous-hermes2
The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.
4K contextQ4_K_MApache License
12 variantsCheck my PC
Upstage10.7B
solar
A compact, yet powerful 10.7B large language model designed for single-turn conversation.
4K contextQ4_K_M
12 variantsCheck my PC
Mistral AI12.0B
mistral-nemo
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
1000K contextQ4_K_MApache License
6 variantsCheck my PC
6 variantsCheck my PC
Ollama Library13.0B
everythinglm
Uncensored Llama2 based model with support for a 16K context window.
16K contextQ4_K_MLLAMA 2 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
Ollama Library13.0B
nexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
16K contextQ4_K_MNexusflow.ai License Terms
12 variantsCheck my PC
Ollama Library13.0B
open-orca-platypus2
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
4K contextQ4_K_M
6 variantsCheck my PC
Ollama Library13.0B
wizard-vicuna
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
2K contextQ4_K_M
6 variantsCheck my PC
6 variantsCheck my PC
Microsoft14.0B
phi4
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
16K contextQ4_K_MMicrosoft.
3 variantsCheck my PC
Microsoft14.0B
phi4-reasoning
Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
32K contextQ4_K_MMicrosoft.
6 variantsCheck my PC
Ollama Library1.5B
deepcoder
DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
128K contextQ4_K_MMIT License
6 variantsCheck my PC
DeepSeek AI16.0B
deepseek-coder-v2
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
4K contextQ4_K_MDEEPSEEK LICENSE AGREEMENT
24 variantsCheck my PC
DeepSeek AI16.0B
deepseek-v2
A strong, economical, and efficient Mixture-of-Experts language model.
4K contextQ4_K_MDEEPSEEK LICENSE AGREEMENT
12 variantsCheck my PC
OpenAI20.0B
gpt-oss
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
128K contextMXFP4Apache License
2 variantsCheck my PC
OpenAI20.0B
gpt-oss-safeguard
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
128K contextMXFP4Apache License
2 variantsCheck my PC
Upstage22.0B
solar-pro
Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU
4K contextQ4_K_MMIT License
6 variantsCheck my PC
Mistral AI22.0B
codestral
Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
32K contextQ4_K_MMistral AI Non-Production License
5 variantsCheck my PC
Mistral AI24.0B
devstral
Devstral: the best open source model for coding agents
128K contextQ4_K_MApache License
3 variantsCheck my PC
Mistral AI24.0B
magistral
Magistral is a small, efficient reasoning model with 24B parameters.
39K contextQ4_K_MApache License
3 variantsCheck my PC
Mistral AI22.0B
mistral-small
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
128K contextQ4_K_MApache License
9 variantsCheck my PC
Ollama Library24.0B
lfm2
LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24…
32K contextQ4_K_MLFM Open License v1.0
2 variantsCheck my PC
Mistral AI24.0B
devstral-small-2
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
384K contextMultimodalQ4_K_M
3 variantsCheck my PC
Mistral AI24.0B
mistral-small3.1
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k…
128K contextMultimodalQ4_K_M
3 variantsCheck my PC
Mistral AI24.0B
mistral-small3.2
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
128K contextMultimodalQ4_K_MApache License
3 variantsCheck my PC
Ollama Library27.0B
clef
Clef is a 27B multimodal model created by Cloudflare that turns a state and a schema of typed questions into decisions.
256K contextMultimodalQ4_K_MApache License
2 variantsCheck my PC
Alibaba Cloud27.0B
qwen3.8
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
256K contextMultimodalQ4_K_MApache License
2 variantsCheck my PC
Ollama Library30.0B
muse-glimmer
Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, l…
128K contextMultimodalQ4_K_M
2 variantsCheck my PC
IBM3.0B
granite4.1
IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented gener…
128K contextQ4_K_MApache License
15 variantsCheck my PC
Alibaba Cloud30.0B
qwen3-coder
Alibaba's performant long context models for agentic and coding tasks.
256K contextQ4_K_MApache License
6 variantsCheck my PC
NVIDIA4.0B
nemotron-3-nano
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
256K contextQ4_K_MNVIDIA Open Model License Agreement
5 variantsCheck my PC
NVIDIA30.0B
nemotron-cascade-2
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
256K contextQ4_K_MNVIDIA Open Model License Agreement
1 variantCheck my PC
Allen Institute for AI32.0B
olmo-3.1
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and p…
64K contextQ4_K_MApache License
6 variantsCheck my PC
Cohere35.0B
command-r
Command R is a Large Language Model optimized for conversational interaction and long context tasks.
128K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International Public
12 variantsCheck my PC
6 variantsCheck my PC
NVIDIA30.0B
nemotron-3.5-lightning
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
1024K contextQ4_K_MNVIDIA Open Model License Agreement
2 variantsCheck my PC
NVIDIA33.0B
nemotron3
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade…
128K contextMultimodalQ4_K_MNVIDIA Open Model License Agreement
1 variantCheck my PC
Ollama Library34.0B
codebooga
A high-performing code instruct model created by merging two existing code models.
16K contextQ4_K_M
6 variantsCheck my PC
Microsoft34.0B
phind-codellama
Code generation model based on Code Llama.
16K contextQ4_K_MLLAMA 2 COMMUNITY LICENSE AGREEMENT
18 variantsCheck my PC
Alibaba Cloud27.0B
qwen3.6
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
256K contextMultimodalQ4_K_MApache License
8 variantsCheck my PC
Ollama Library40.0B
alfred
A robust conversational model designed to be used for both chat and instruct use cases.
2K contextQ4_0
2 variantsCheck my PC
Ollama Library56.0B
dolphin-mixtral
Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
32K contextQ4_K_MApache License
24 variantsCheck my PC
Mistral AI56.0B
mixtral
A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
32K contextQ4_K_MApache License
24 variantsCheck my PC
Ollama Library56.0B
nous-hermes2-mixtral
The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
32K contextQ4_K_MApache License
6 variantsCheck my PC
Mistral AI56.0B
Mixtral 8x7B
Mistral AI's Mixtral 8x7B — sparse Mixture of Experts model. 46.7B total params, ~12.9B active per token.
Q4_K_MApache-2.0
1 variantCheck my PC
Ollama Library56.0B
notux
A top-performing mixture of experts model, fine-tuned with high-quality data.
32K contextQ4_K_MMIT License
6 variantsCheck my PC
29 variantsCheck my PC
Ollama Library70.0B
firefunction-v2
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
8K contextQ4_K_MMETA LLAMA 3 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
Meta AI70.0B
llama3.3
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
128K contextQ4_K_MLLAMA 3.3 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
NVIDIA70.0B
nemotron
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
128K contextQ4_K_MLLAMA 3.1 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
Ollama Library70.0B
r1-1776
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
128K contextQ4_K_MMIT License
6 variantsCheck my PC
Ollama Library70.0B
reflection
A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct cour…
128K contextQ4_K_MLLAMA 3.1 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
Ollama Library72.0B
athene-v2
Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.
32K contextQ4_K_MNexusflow.ai License Terms for Personal Use
6 variantsCheck my PC
Alibaba Cloud80.0B
qwen3-next
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
256K contextQ4_K_MApache License
6 variantsCheck my PC
Cohere104.0B
command-r-plus
Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.
128K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International Public
9 variantsCheck my PC
Meta AI17.0B
llama4
Meta's latest collection of multimodal models.
10240K contextMultimodalQ4_K_M**LLAMA 4 COMMUNITY LICENSE AGREEMENT**
6 variantsCheck my PC
Cohere111.0B
command-a
111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
16K contextQ4_K_MCreative Commons Attribution-NonCommercial 4.0 International Public
3 variantsCheck my PC
Ollama Library120.0B
goliath
A language model created by combining two fine-tuned Llama 2 70B models into one.
4K contextQ4_K_M
6 variantsCheck my PC
Ollama Library120.0B
megadolphin
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
4K contextQ4_K_MLLAMA 2 COMMUNITY LICENSE AGREEMENT
6 variantsCheck my PC
Mistral AI123.0B
mistral-large
Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context w…
32K contextQ4_K_MMistral AI Research License
12 variantsCheck my PC
NVIDIA120.0B
nemotron-3-super
NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-…
256K contextQ4_K_MNVIDIA Software and Model Evaluation License
2 variantsCheck my PC
Mistral AI123.0B
devstral-2
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
256K contextQ4_K_M
3 variantsCheck my PC
Mistral AI128.0B
mistral-medium-3.5
Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.
256K contextMultimodalQ4_K_M
2 variantsCheck my PC
Databricks132.0B
dbrx
DBRX is an open, general-purpose LLM created by Databricks.
32K contextQ4_0Databricks Open Model License
3 variantsCheck my PC
Alibaba Cloud125.0B
qwen3.8-flash-next
This experimental preview of the architecture that will underpin Qwen4.
256K contextMultimodalQ4_K_MQwen Community License 1.0
2 variantsCheck my PC
DeepSeek AI236.0B
deepseek-v2.5
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
4K contextQ4_0DEEPSEEK LICENSE AGREEMENT
2 variantsCheck my PC
Ollama Library9.0B
ornith-1.5
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
256K contextMultimodalQ4_K_M
3 variantsCheck my PC
Ollama Library671.0B
cogito-2.1
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
160K contextQ4_K_MMIT License
3 variantsCheck my PC
DeepSeek AI671.0B
deepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
160K contextQ4_K_MDEEPSEEK LICENSE AGREEMENT
3 variantsCheck my PC
DeepSeek AI671.0B
deepseek-v3.1
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
160K contextQ4_K_MMIT License
5 variantsCheck my PC
Browse by hardware instead
If you know your graphics card or how much VRAM it has, start there — browse by graphics card to see which of these models fit.