NVIDIA · 10GB VRAM
A GeForce RTX 3080 has 10GB of VRAM. Checked against 225 models from the Ollama library, 162 have good/excellent reference fits on the GPU at 4K context and 40 more run with part of the model in system RAM.
162
run well
40
with trade-offs
225
builds evaluated
This is the original 10 GB, 320-bit RTX 3080. The 12 GB version has a different capacity and interface; use a 12 GB reference estimate for that variant.
ollama ps. Intel Macs use the Ollama CPU path; Apple Silicon uses its integrated Metal GPU.Hardware specifications · Ollama support table · reviewed 2026-09-15.
Compare GeForce RTX 3060 12GB (12 GB). Use the same model, quantization and context to see what the capacity difference changes.
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.
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
Est. memory 2.9 GB · medium confidence
Model fully fits in usable GPU VRAM.
ollama run llama3.2:3bAn 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
Est. memory 5.8 GB · medium confidence
Model fully fits in usable GPU VRAM.
ollama run llama3.1:8bA 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
Est. memory 5.3 GB · medium confidence
Model fully fits in usable GPU VRAM.
ollama run qwen2.5-coder:7bA 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
Est. memory 10.2 GB · medium confidence
Estimated 88% of layers offloaded to GPU (42/48); model does not fully fit in VRAM.
ollama run qwen2.5:14bAfter 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.
Largest first — these have good/excellent reference fits with 10GB of VRAM at 4K context. A good fit can include a small estimated CPU offload. These are technical defaults, not a quality ranking.
| Model | Build | Memory needed | Verdict |
|---|---|---|---|
| llama3.2-visionMeta AI | llama3.2-vision:11bQ4_K_M | ~8.9 GB | Good fit |
| mistral-nemoMistral AI | mistral-nemo:12b-instruct-2407-q4_K_MQ4_K_M | ~8.5 GB | Good fit |
| falcon2TII | falcon2:11b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens. | ~8.2 GB | Good fit |
| llama-proMeta AI | llama-pro:8b-text-q4_K_MQ4_K_M | ~8.0 GB | Good fit |
| nous-hermes2Ollama Library | nous-hermes2:10.7b-solar-q4_K_MQ4_K_M | ~7.6 GB | Good fit |
| solarUpstage | solar:10.7b-text-v1-q4_K_MQ4_K_M | ~7.6 GB | Good fit |
| deepseek-ocrDeepSeek AI | deepseek-ocr:3bF16 | ~7.4 GB | Excellent fit |
| olmo2Allen Institute for AI | olmo2:7bQ4_K_M | ~6.9 GB | Excellent fit |
| olmo-3Allen Institute for AI | olmo-3:7b-instruct-q4_K_MQ4_K_M | ~6.9 GB | Excellent fit |
| codegeex4Zhipu AI | codegeex4:9b-all-q4_K_MQ4_K_M | ~6.8 GB | Excellent fit |
| glm4Zhipu AI | glm4:9b-text-q4_K_MQ4_K_M | ~6.8 GB | Excellent fit |
| nimble-v3Ollama Library | nimble-v3:9b-q4_K_MQ4_K_M | ~6.6 GB | Excellent fit |
| ornith-1.5Ollama Library | ornith-1.5:9bQ4_K_M | ~6.6 GB | Excellent fit |
| nimbleOllama Library | nimble:9b-q4_K_MQ4_K_M | ~6.6 GB | Excellent fit |
| ornithOllama Library | ornith:9bQ4_K_M | ~6.6 GB | Excellent fit |
| nemotron-3-nanoNVIDIA | nemotron-3-nano:4bQ4_K_M | ~6.5 GB | Excellent fit |
| deepseek-llmDeepSeek AI | deepseek-llm:7b-base-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
| llama2Meta AI | llama2:7b-text-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
| duckdb-nsqlOllama Library | duckdb-nsql:7b-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
| orca2Ollama Library | orca2:7b-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
| wizardcoderOllama Library | wizardcoder:7b-python-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
| wizard-mathOllama Library | wizard-math:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens. | ~6.5 GB | Excellent fit |
| wizardlmOllama Library | wizardlm:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens. | ~6.5 GB | Excellent fit |
| magicoderOllama Library | magicoder:7b-s-cl-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
| llavaOllama Library | llava:7b-v1.5-q4_K_MQ4_K_M | ~6.5 GB | Excellent fit |
Showing the 25 largest of 162 models that run well.
Each model is evaluated at 4K context against 10GB of VRAM, counting model weights, KV cache, compute buffers and runtime overhead, minus a reserve for the display and operating system. Download sizes come from the official Ollama registry.
Reference scenario: Windows 11, 32GB of system RAM, an illustrative 8-core/16-thread CPU and 500GB free disk. Available RAM, driver version and free VRAM are unknown; the engine applies reserves. Supported GPU drivers/backends are assumed installed. Your own machine may differ — RAM, free disk space and whether an acceleration backend is actually installed all change the answer, which is what the PC scan measures directly.