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 4 quants, from 14.3 GB (Q4_K_M) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
24 B parameter Mistral model for agentic coding tasks
Devstral‑Small‑2507 is a 24 billion‑parameter LLM fine‑tuned for software engineering. It supports a 128k‑token context window and is text‑only. The model is released under Apache 2.0 and can be run locally with GGUF quantizations.
Good at
- Agentic coding with tool use
- Editing multiple files
- Function calling
Limits
- No vision support
- Requires 128k context for full capability
- Large memory for higher quantizations
Best for
- Local coding assistants
- OpenHands agent integration
- On‑device software engineering
Who it’s for. Developers and teams needing a lightweight, open‑source coding agent 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 → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (14.33 GB file, ~16.2 GB VRAM at 8k context). For 12 GB VRAM, Q5_K_M (16.76 GB file, ~18.6 GB VRAM). For 24 GB VRAM, Q8_0 (25.05 GB file, ~26.9 GB VRAM). BF16 requires ~49 GB VRAM and is not recommended for typical consumer GPUs.
What GPU do you need for 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 Q5_K_M (16.8 GB file, about 18.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
Which devstral-small-2507 quant should you choose?
Q4_K_M is the usual starting point for 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 devstral-small-2507
How much VRAM does 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 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 devstral-small-2507 GGUF?
It depends on the quant: Q4_K_M is 14.3 GB, Q5_K_M is 16.8 GB, Q8_0 is 25.1 GB, BF16 is 47.2 GB.
What context length does 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 devstral-small-2507 GGUF?
The files are on Hugging Face in the mistralai/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 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?
Yes, the Q4_K_M or Q5_K_M quantizations fit within the 24 GB VRAM of an RTX 4090, allowing local inference.
Does the model support vision or image input?
No, the model is text‑only; the vision encoder was removed during fine‑tuning.
What license applies to this model?
The model is released under the Apache 2.0 license, permitting commercial and non‑commercial use.