How much VRAM does Mistral Nemo 12B Instruct need?

About 8.4 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 13.2 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will Mistral Nemo 12B Instruct run on a 10GB GPU?

Yes — at Q4_K_M and 4K context it needs about 8.4 GB, which leaves 1.6 GB spare on a Arc B570 10G, or on any of the other 10 GB cards here (2 in all). That is the smallest size in this index that clears it comfortably; 67 of 78 do.

Which quantization of Mistral Nemo 12B Instruct should I use?

Q6_K has the lowest published quality loss (0.9%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q6_K, AWQ INT4.

Mistral Nemo 12B Instruct

12B

Mistral AI

Mistral + NVIDIA collaboration. 128K context, excellent multilingual support.

⬇ 24.2K HF downloads♥ 133 likesbartowski/Mistral-Nemo-Instruct-2407-GGUF· stats from 10/20/2026

Consumer GPUMac / Apple Silicon

131K

Max Context

Quant Variants

GGUF Q6_K

Best Quality

99.1%

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	Q4_K_M	4.85	8.5 GB	3.1%	112 tok/s	Estimated	Calc HF
GGUF	Q6_K	6.56	11.0 GB	0.9%	95 tok/s	Estimated	Calc HF
AWQ	INT4	4	7.8 GB	4.4%	148 tok/s	Estimated	Calc HF

Similar models

Compare with Mistral 7B

Mistral 7B Instruct v0.3

Mistral AI

Consumer GPUMac / Apple Silicon

4.6 GBmin VRAM99.1%accuracy

Classic Mistral 7B v0.3. Still a reliable baseline for local chat APIs.

24B

Mistral Small 24B Instruct

Mistral AI

Consumer GPUPro GPU

13.5 GBmin VRAM97.8%accuracy

Mistral's efficient 24B. Strong multilingual; fits on 24GB with Q4.

47B MoE

Mixtral 8x7B Instruct

Mistral AI

Pro GPU

25.2 GBmin VRAM97.2%accuracy

Classic MoE model. ~13B active params per token; needs 32GB+ VRAM for Q4.

675B MoE

Mistral Large 3 675B Instruct

Mistral AI

Pro GPU

312.0 GBmin VRAM97.9%accuracy

Mistral 3 flagship MoE (41B active / 675B total) with vision encoder. FP8 on 8×H200; GGUF quant for research clusters only. Its attention is DeepSeek-style MLA, so the real KV cache is smaller than the figure below, which uses an unverified conventional layout. At 32K that is a rounding error beside ~390 GB of weights; at the full 256K window, treat the cache figure as an upper bound.

Running Mistral Nemo 12B Instruct locally

At Q4_K_M and 4K of context, Mistral Nemo 12B Instruct needs about 8.4 GB — 7.0 GB of weights, 0.63 GB of KV cache and a 0.8 GB activation buffer. The smallest cards in this index that clear that comfortably are 10 GB ones — 2 of them, from the Arc B570 10G up — and 67 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 4.37 GB, taking the total to 13.2 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 30 GB.

Which build to download

This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q6_K carries the lowest published perplexity loss at 0.9%. The fastest level listed is AWQ INT4 at about 148 tok/s on an RTX 4090, batch 1 — an estimate, not a run on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.

Common questions

How much VRAM does Mistral Nemo 12B Instruct need?: About 8.4 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 13.2 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will Mistral Nemo 12B Instruct run on a 10GB GPU?: Yes — at Q4_K_M and 4K context it needs about 8.4 GB, which leaves 1.6 GB spare on a Arc B570 10G, or on any of the other 10 GB cards here (2 in all). That is the smallest size in this index that clears it comfortably; 67 of 78 do.
Which quantization of Mistral Nemo 12B Instruct should I use?: Q6_K has the lowest published quality loss (0.9%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q6_K, AWQ INT4.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Runs comfortably on: Arc B570 10G10GB · +1.6 RTX 3080 10G10GB · +1.6 RTX 3060 12G12GB · +3.6 Radeon RX 6700 XT12GB · +3.6 Radeon RX 7700 XT12GB · +3.6
Just misses: RTX 4060+0.4GB over RTX 4060 Ti 8G+0.4GB over
Ships in: GGUF AWQ
Compared here: GGUF vs AWQ
Try it yourself: Size it in the calculator Generate the run command

How to actually run this

Deployment guides for this model and this class of hardware.

This page's figures change when the model or the runtime does.Last updated 2026-10-20 RSS → /feed.xml