How much VRAM does Devstral Small 1.1 24B need?

About 15.6 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 20.4 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 Devstral Small 1.1 24B run on a 20GB GPU?

Yes — at Q4_K_M and 4K context it needs about 15.6 GB, which leaves 4.4 GB spare on a Radeon RX 7900 XT. That is the smallest card in this index that clears it comfortably; 31 of 63 do.

Which quantization of Devstral Small 1.1 24B should I use?

Q6_K has the lowest published quality loss (0.6%), and Q4_K_M is the level most people run. All 5 levels in the index are Q4_K_M, Q5_K_M, Q6_K, AWQ INT4, EXL2 4.65bpw.

Devstral Small 1.1 24B

24B

Mistral Devstral

Mistral + All Hands agentic coding model on a Mistral Small 3.1 base. Built for repo-scale tool use rather than single-file completion. Q4 ~14GB fits a 16GB card.

⬇ 71.9K HF downloads♥ 368 likesmistralai/Devstral-Small-2507· stats from 9/21/2026

Consumer GPUMac / Apple Silicon

131K

Max Context

Quant Variants

GGUF Q6_K

Best Quality

99.4%

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

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

Measured = site benchmarks · Estimated = formula · Community = public reports

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	Q4_K_M	4.85	14.3 GB	2.9%	62 tok/s	Community	Calc HF
GGUF	Q5_K_M	5.68	16.8 GB	1.4%	55 tok/s	Estimated	Calc HF
GGUF	Q6_K	6.56	19.4 GB	0.6%	48 tok/s	Estimated	Calc HF
AWQ	INT4	4	13.0 GB	4.0%	78 tok/s	Estimated	Calc HF
EXL2	4.65bpw	4.65	13.9 GB	2.5%	88 tok/s	Estimated	Calc HF

Similar models

Compare with Qwen3 30B-A3B

30B-A3B

Qwen3 30B-A3B Instruct

Alibaba Qwen3

Consumer GPUMac / Apple Silicon

17.5 GBmin VRAM98.9%accuracy

Qwen3 MoE with only 3B active params. Q4 ~19GB file; outperforms QwQ-32B on 16GB cards.

30B-A3B

Qwen3-Coder 30B-A3B Instruct

Alibaba Qwen3

Consumer GPUMac / Apple Silicon

17.8 GBmin VRAM99.0%accuracy

Agentic coding MoE with 3.3B active params and 256K native context. Top open coder for 16–24GB cards.

21B MoE

GPT-OSS 20B

OpenAI GPT-OSS

Consumer GPUMac / Apple Silicon

11.9 GBmin VRAM100.0%accuracy

OpenAI open-weight MoE (21B total / 3.6B active), shipped natively in MXFP4 — ~12.8GB runs on a 16GB card with no quality tax. Only 3.6B active params means CPU-offload stays usable.

36B

Seed-OSS 36B Instruct

ByteDance Seed

Consumer GPUPro GPU

17.4 GBmin VRAM98.7%accuracy

Dense 36B with a native 512K context. Q4 weights are ~22GB, which lands on a 24GB card or a 2×16GB split — but the context is the real cost: 512K of KV cache is roughly 128GB on its own, so budget context first and weights second.

Running Devstral Small 1.1 24B locally

At Q4_K_M and 4K of context, Devstral Small 1.1 24B needs about 15.6 GB — 13.6 GB of weights, 0.63 GB of KV cache and a 1.4 GB activation buffer. The smallest card in this index that clears that comfortably is the Radeon RX 7900 XT at 20 GB, and 31 of the 63 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 20.4 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 37 GB.

Which build to download

This index tracks 3 formats for it — GGUF, AWQ, EXL2 — across 5 levels. Q6_K carries the lowest published perplexity loss at 0.6%. The fastest level measured here is EXL2 4.65bpw at 88 tok/s on an RTX 4090, batch 1. 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 and CUDA only.

Common questions

How much VRAM does Devstral Small 1.1 24B need?: About 15.6 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 20.4 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 Devstral Small 1.1 24B run on a 20GB GPU?: Yes — at Q4_K_M and 4K context it needs about 15.6 GB, which leaves 4.4 GB spare on a Radeon RX 7900 XT. That is the smallest card in this index that clears it comfortably; 31 of 63 do.
Which quantization of Devstral Small 1.1 24B should I use?: Q6_K has the lowest published quality loss (0.6%), and Q4_K_M is the level most people run. All 5 levels in the index are Q4_K_M, Q5_K_M, Q6_K, AWQ INT4, EXL2 4.65bpw.

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: Radeon RX 7900 XT20GB · +4.4 RTX 409024GB · +8.4 RTX 309024GB · +8.4 Tesla P40 24G24GB · +8.4 Mac M4 Pro 24G24GB · +2.4
Tight but possible: RTX 508016GB RTX 5070 Ti16GB RTX 5060 Ti 16G16GB
Just misses: Mac M3 16G+3.6GB over Mac M3 Pro 18G+2.1GB over
Ships in: GGUF AWQ EXL2
Compared here: GGUF vs AWQ GGUF vs EXL2 AWQ vs EXL2
A top pick for: Best local LLM for 16GB
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 2026-09-21 RSS → /feed.xml