CanMyPCRunAILocal AI compatibility

What AI models can you run with 10GB of VRAM?

With 10GB of VRAM, 162 of 225 catalog builds have good/excellent reference fits at 4K context. 40 more run by offloading part of the model to system RAM, which works but is slower.

162

run well

40

with trade-offs

225

builds evaluated

Check my actual PC

Check the exact 3080 variant

The original RTX 3080 has 10 GB, while a later version has 12 GB. A guide written for the 12 GB version can overstate what fits here. Use this budget if your card is the 10 GB model.

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 88% of layers offloaded to GPU (42/48); 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 10GB of VRAM

Heaviest first — each of these has a good/excellent reference fit with 10GB at 4K context, counting weights, KV cache, compute buffers and runtime overhead.

Models that fit in 10GB of VRAM
ModelBuildMemory neededVerdict
llama3.2-visionllama3.2-vision:11bQ4_K_M~8.9 GBGood fit
mistral-nemomistral-nemo:12b-instruct-2407-q4_K_MQ4_K_M~8.5 GBGood fit
falcon2falcon2:11b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~8.2 GBGood fit
llama-prollama-pro:8b-text-q4_K_MQ4_K_M~8.0 GBGood fit
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 GBExcellent fit
olmo2olmo2:7bQ4_K_M~6.9 GBExcellent fit
olmo-3olmo-3:7b-instruct-q4_K_MQ4_K_M~6.9 GBExcellent fit
codegeex4codegeex4:9b-all-q4_K_MQ4_K_M~6.8 GBExcellent fit
glm4glm4:9b-text-q4_K_MQ4_K_M~6.8 GBExcellent fit
nimble-v3nimble-v3:9b-q4_K_MQ4_K_M~6.6 GBExcellent fit
ornith-1.5ornith-1.5:9bQ4_K_M~6.6 GBExcellent fit
nimblenimble:9b-q4_K_MQ4_K_M~6.6 GBExcellent fit
ornithornith:9bQ4_K_M~6.6 GBExcellent fit
nemotron-3-nanonemotron-3-nano:4bQ4_K_M~6.5 GBExcellent fit
deepseek-llmdeepseek-llm:7b-base-q4_K_MQ4_K_M~6.5 GBExcellent fit
llama2llama2:7b-text-q4_K_MQ4_K_M~6.5 GBExcellent fit
duckdb-nsqlduckdb-nsql:7b-q4_K_MQ4_K_M~6.5 GBExcellent fit
orca2orca2:7b-q4_K_MQ4_K_M~6.5 GBExcellent fit
wizardcoderwizardcoder:7b-python-q4_K_MQ4_K_M~6.5 GBExcellent fit
wizard-mathwizard-math:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~6.5 GBExcellent fit
wizardlmwizardlm:7b-q4_K_MQ4_K_MMemory scenario exceeds documented maximum of 2,048 tokens.~6.5 GBExcellent fit
magicodermagicoder:7b-s-cl-q4_K_MQ4_K_M~6.5 GBExcellent fit
llavallava:7b-v1.5-q4_K_MQ4_K_M~6.5 GBExcellent fit

Graphics cards with 10GB of VRAM

GeForce RTX 3080

How this was calculated

Every model is evaluated at 4K context against 10GB 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.

10GB VRAM and local AI — frequently asked questions

Is 10GB of VRAM enough to run AI models locally?
Yes — 162 of the 225 builds evaluated have good/excellent reference fits with 10GB at 4K context, and 40 more run with part of the model offloaded to system RAM. The heaviest that fits is llama3.2-vision:11b, needing about 8.9 GB.
How should I choose a model for 10GB VRAM?
Choose for your task, then check memory. llama3.2-vision (llama3.2-vision:11b) 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 10GB of VRAM?
Cards with 10GB include GeForce RTX 3080.

Other VRAM amounts

4GB6GB8GB12GB16GB24GB32GB