CanMyPCRunAILocal AI compatibility

What AI models can you run with 8GB of VRAM?

With 8GB of VRAM, 158 of 225 catalog builds have good/excellent reference fits at 4K context. 44 more run by offloading part of the model to system RAM, which works but is slower.

158

run well

44

with trade-offs

225

builds evaluated

Check my actual PC

Choose task fit before using every gigabyte

At 8 GB, the code-focused and general-chat examples answer different questions. Keep their quantization fixed while changing context to see which retains headroom. An 8 GB laptop GPU and an 8 GB desktop GPU need separate driver and speed checks.

Quantization compresses weights; it does not remove context-cache or runtime costs. Compare the same model at Q4 and Q8 in the calculator, then validate its output on your task. Training and fine-tuning need a different memory budget.

Change system RAM and contextCompare exact builds8 GB vs 12 GB vs 16 GB

Four builds to compare by task

Editorial examples chosen for their documented tasks, all Q4_K_M at 4,096 tokens. Check the verdict before downloading. These are estimates, not benchmark rankings.

Short conversations and summaries

llama3.2:3b

A small instruction-tuned model for trying local chat with more memory headroom. Review summaries against the source text.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 2.9 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run llama3.2:3b

General instruction following

llama3.1:8b

An 8B instruction-tuned alternative to compare on your own prompts. It needs more memory than the 3B example and can still give incorrect answers.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 5.8 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run llama3.1:8b

Code explanation and editing

qwen2.5-coder:7b

A code-focused instruct build. Review generated changes and run your tests; a memory fit is not evidence that its code is correct.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 5.3 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run qwen2.5-coder:7b

A larger general-purpose comparison

qwen2.5:14b

A 14B instruct build for comparing answers when memory allows. Larger size does not establish better results for every task.

Task and build source · Catalog checked 2026-10-13

Runs with trade-offs

Est. memory 10.2 GB · high confidence

Estimated 69% of layers offloaded to GPU (33/48); model does not fully fit in VRAM.

ollama run qwen2.5:14b

After opening Ollama's prompt, enter /set parameter num_ctx 4096 to match this calculation, within the model's supported maximum. Install a current Ollama release that supports the build. Setup and troubleshooting.

Models that fit — largest memory first — for 8GB of VRAM

Heaviest first — each of these has a good/excellent reference fit with 8GB at 4K context, counting weights, KV cache, compute buffers and runtime overhead.

Models that fit in 8GB of VRAM
ModelBuildMemory neededVerdict
nous-hermes2nous-hermes2:10.7b-solar-q4_K_MQ4_K_M~7.6 GBGood fit
solarsolar:10.7b-text-v1-q4_K_MQ4_K_M~7.6 GBGood fit
deepseek-ocrdeepseek-ocr:3bF16~7.4 GBGood fit
olmo2olmo2:7bQ4_K_M~6.9 GBGood fit
olmo-3olmo-3:7b-instruct-q4_K_MQ4_K_M~6.9 GBGood fit
codegeex4codegeex4:9b-all-q4_K_MQ4_K_M~6.8 GBGood fit
glm4glm4:9b-text-q4_K_MQ4_K_M~6.8 GBGood fit
nimble-v3nimble-v3:9b-q4_K_MQ4_K_M~6.6 GBGood fit
ornith-1.5ornith-1.5:9bQ4_K_M~6.6 GBGood fit
nimblenimble:9b-q4_K_MQ4_K_M~6.6 GBGood fit
ornithornith:9bQ4_K_M~6.6 GBGood fit
nemotron-3-nanonemotron-3-nano:4bQ4_K_M~6.5 GBGood fit
deepseek-llmdeepseek-llm:7b-base-q4_K_MQ4_K_M~6.5 GBGood fit
llama2llama2:7b-text-q4_K_MQ4_K_M~6.5 GBGood fit
duckdb-nsqlduckdb-nsql:7b-q4_K_MQ4_K_M~6.5 GBGood fit
orca2orca2:7b-q4_K_MQ4_K_M~6.5 GBGood fit
wizardcoderwizardcoder:7b-python-q4_K_MQ4_K_M~6.5 GBGood fit
wizard-mathwizard-math:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~6.5 GBGood fit
wizardlmwizardlm:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~6.5 GBGood fit
magicodermagicoder:7b-s-cl-q4_K_MQ4_K_M~6.5 GBGood fit
llavallava:7b-v1.5-q4_K_MQ4_K_M~6.5 GBGood fit
codellamacodellama:7b-python-q4_K_MQ4_K_M~6.5 GBGood fit
meditronmeditron:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~6.5 GBGood fit
orca-miniorca-mini:7b-v2-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~6.5 GBGood fit
llama2-chinesellama2-chinese:7b-chat-q4_K_MQ4_K_M~6.5 GBGood fit

Graphics cards with 8GB of VRAM

GeForce RTX 5060GeForce RTX 4060 Ti 8GBGeForce RTX 4060GeForce RTX 3070GeForce RTX 3060 TiGeForce RTX 3050 8GBRadeon RX 7600

How this was calculated

Every model is evaluated at 4K context against 8GB of VRAM, minus a reserve for the display and operating system, and assuming 32GB of system RAM with an illustrative 8-core/16-thread CPU and 500GB free disk. Available RAM and GPU budget/free memory are unknown. A working Vulkan backend on Windows is assumed; this is a capacity scenario, not a claim that all cards with this much memory have the same support. Your own machine may differ, which is what the PC scan measures directly.

8GB VRAM and local AI — frequently asked questions

Is 8GB of VRAM enough to run AI models locally?
Yes — 158 of the 225 builds evaluated have good/excellent reference fits with 8GB at 4K context, and 44 more run with part of the model offloaded to system RAM. The heaviest that fits is nous-hermes2:10.7b-solar-q4_K_M, needing about 7.6 GB.
How should I choose a model for 8GB VRAM?
Choose for your task, then check memory. nous-hermes2 (nous-hermes2:10.7b-solar-q4_K_M) is the heaviest catalog default that fits this reference budget; its size does not establish answer quality. Smaller models leave headroom for a longer context window, which often matters more than raw parameter count.
Which graphics cards have 8GB of VRAM?
Cards with 8GB include GeForce RTX 5060, GeForce RTX 4060 Ti 8GB, GeForce RTX 4060, GeForce RTX 3070, GeForce RTX 3060 Ti, GeForce RTX 3050 8GB, Radeon RX 7600.

Other VRAM amounts

4GB6GB10GB12GB16GB24GB32GB