Devstral Small 1.1 24B
24BMistral 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. At Q4_K_M it needs about 15.7 GB at 4K, tight on a 16 GB card and comfortable on 20 GB.
131K
Max Context
5
Quant Variants
GGUF Q6_K
Best Quality
+0.6%
Perplexity rise (best build)
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 | 4.86 | 15.7 GB | 2.9% | 62 tok/s | Community | |
| GGUF | Q5_K_M | 5.69 | 18.2 GB | 1.4% | 55 tok/s | Estimated | |
| GGUF | Q6_K | 6.56 | 20.9 GB | 0.6% | 48 tok/s | Estimated | |
| AWQ | INT4 | 4 | 13.0 GB | 4.0% | 78 tok/s | Estimated | |
| EXL2 | 4.65bpw | 4.65 | 15.0 GB | 2.5% | — | Estimated |
Which file each size is for
A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB (1024³ bytes) with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector (mmproj), where the repo ships one, is a separate download and is in neither number.
- GGUF Q4_K_Mbartowski/mistralai_Devstral-Small-2507-GGUF · mistralai_Devstral-Small-2507-Q4_K_M.gguf · 14.33 GB (14,333,916,096 bytes) · + vision projector 0.88 GB, separate · listing read 2026-11-03
- GGUF Q5_K_Mbartowski/mistralai_Devstral-Small-2507-GGUF · mistralai_Devstral-Small-2507-Q5_K_M.gguf · 16.76 GB (16,763,990,976 bytes) · + vision projector 0.88 GB, separate · listing read 2026-11-03
- GGUF Q6_Kbartowski/mistralai_Devstral-Small-2507-GGUF · mistralai_Devstral-Small-2507-Q6_K.gguf · 19.35 GB (19,345,945,536 bytes) · + vision projector 0.88 GB, separate · listing read 2026-11-03
- AWQ INT4Sized at the calculator's generic rate for this level; no file was checked.
- EXL2 4.65bpwSized at the calculator's generic rate for this level; no file was checked.
Similar models
Compare with Qwen3 30B-A3BQwen3 30B-A3B Instruct
Alibaba Qwen3
Qwen3 MoE with only 3B active params. Q4 ~19GB file; outperforms QwQ-32B on 16GB cards.
Qwen3-Coder 30B-A3B Instruct
Alibaba Qwen3
Agentic coding MoE with 3.3B active params and 256K native context. Top open coder for 16–24GB cards.
GPT-OSS 20B
OpenAI GPT-OSS
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.
Seed-OSS 36B Instruct
ByteDance Seed
Dense 36B with a native 512K context. The Q4_K_M file is 21.8 GB, so with cache and buffers it needs about 23.9 GB at 4K: tight on a 24 GB card, where Q3_K_M (19.5 GB) is the comfortable choice, or a 2×16GB split. The AWQ build is 21.1 GB, not the 4-bit rate the name suggests. 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 15.7 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 34 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 20.5 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 listed is AWQ INT4 at about 78 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 Devstral Small 1.1 24B need?
- About 15.7 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 20.5 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 15.7 GB, which leaves 4.3 GB spare on a Radeon RX 7900 XT. That is the smallest card in this index that clears it comfortably; 34 of 78 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 · +4.3Mac M4 24G24GB · +2.3Mac M4 Pro 24G24GB · +2.3RTX 309024GB · +8.3Radeon RX 7900 XTX24GB · +8.3
- Tight but possible
- RTX 4060 Ti 16G16GBRadeon RX 7600 XT16GBRadeon RX 9060 XT 16G16GB
- Compared here
- GGUF vs AWQGGUF vs EXL2AWQ vs EXL2
- A top pick for
- Best local LLM for 16GB
- Try it yourself
- Size it in the calculatorGenerate 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 2026-11-07 RSS → /feed.xml