mistralai_Devstral Small 2505 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 12.4 GB (Q3_K_L) to 25.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Devstral Small 2505 – 23.6B parameter coding agent
Devstral Small 2505 is a 23.6 billion parameter LLM fine‑tuned for software engineering tasks. It supports a 131072 token context window and is licensed under Apache‑2.0. The model is text‑only, with no vision capability.
Good at
- Agentic coding
- Tool‑based code exploration
- Editing multiple files
Limits
- No vision support
- Requires 131072 token context
- Apache‑2.0 license
Best for
- Local coding assistants
- Automated codebase refactoring
- Software engineering agents
Who it’s for. Developers and teams needing a lightweight, open‑source model for agentic coding tasks. The model runs on a single RTX 4090 or a Mac with 32 GB RAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 12.4 GB | 14.2 GB | Too big | Get file → | |
| 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, use Q3_K_L (12.4 GB file, 14.2 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (14.33 GB file, 16.2 GB memory). For 16 GB VRAM, Q6_K (19.35 GB file, 21.2 GB memory). For 24 GB VRAM, Q8_0 (25.05 GB file, 26.9 GB memory). Memory estimates are approximate.
What GPU do you need for mistralai_Devstral Small 2505?
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: the best quant that fits is Q3_K_L (12.4 GB file, about 14.2 GB in use).
- 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 2505 quant should you choose?
Q4_K_M is the usual starting point for mistralai_Devstral Small 2505: 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.
If memory is tight, the smallest file is Q3_K_L at 12.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mistralai_Devstral Small 2505
How much VRAM does mistralai_Devstral Small 2505 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 2505 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of mistralai_Devstral Small 2505 GGUF?
It depends on the quant: Q3_K_L is 12.4 GB, 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 2505 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 2505 GGUF?
The files are on Hugging Face in the lmstudio-community/Devstral-Small-2505-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 2505 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 2505 on an RTX 4090?
Yes, the 24 GB VRAM of an RTX 4090 can run the Q4_K_M or Q6_K quantizations with sufficient swap.
Does the model support image input?
No, Devstral Small 2505 is text‑only and has no vision encoder.
What context length does it support?
It supports a context length of 131072 tokens.