mistralai_Devstral Small 2507 needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 14.3 GB (Q4_K_M) to 25.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Devstral Small 2507 – a lightweight, 23.6B‑parameter coding LLM
Devstral Small 2507 is a 23.6 billion‑parameter model fine‑tuned from Mistral‑Small‑3.1 for agentic coding tasks. It offers a 128k‑token context window and is licensed under Apache‑2.0. The model is text‑only and supports Mistral’s function‑calling format.
Good at
- Agentic coding
- Tool‑based code editing
- Large context handling
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license only
Best for
- Local coding assistants
- OpenHands integration
- Software engineering agents
Who it’s for. Developers and teams needing a compact, high‑performance coding model that runs on a single RTX 4090 or a Mac with 32 GB RAM. The model is suitable for local deployment and on‑device use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → |
For 8 GB VRAM, the Q4_K_M quant (14.33 GB file) is recommended; it uses an estimated 16.2 GB at 8k context, which is close to the budget. If more VRAM is available, Q6_K (19.35 GB, 21.2 GB memory) or Q8_0 (25.05 GB, 26.9 GB memory) can be used for higher precision.
What GPU do you need for mistralai_Devstral Small 2507?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (19.3 GB file, about 21.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
Which mistralai_Devstral Small 2507 quant should you choose?
Q4_K_M is the usual starting point for mistralai_Devstral Small 2507: it balances file size and quality well. Here it is a 14.3 GB file.
The Q8_0 file is 25.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mistralai_Devstral Small 2507
How much VRAM does mistralai_Devstral Small 2507 need?
About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run mistralai_Devstral Small 2507 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of mistralai_Devstral Small 2507 GGUF?
It depends on the quant: Q4_K_M is 14.3 GB, Q6_K is 19.3 GB, Q8_0 is 25.1 GB.
What context length does mistralai_Devstral Small 2507 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download mistralai_Devstral Small 2507 GGUF?
The files are on Hugging Face in the lmstudio-community/Devstral-Small-2507-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does mistralai_Devstral Small 2507 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Devstral Small 2507 on an RTX 4090 with 8 GB VRAM?
The Q4_K_M quant uses about 16.2 GB at 8k context, so 8 GB VRAM is insufficient. A larger VRAM GPU is required.
Does the model support image inputs?
No, Devstral Small 2507 is text‑only; the vision encoder was removed before fine‑tuning.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.