Mistralai Devstral Small 2 24B Instruct 2512 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. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Devstral Small 2 24B Instruct 2512 – agentic coding LLM
Devstral Small 2 24B Instruct 2512 is a 23.6 billion‑parameter model built on the Mistral3 architecture. It is fine‑tuned in FP8 for instruction following and excels at software engineering tasks, including tool use and multi‑file editing.
Good at
- Agentic coding and tool use
- Instruction following
- Software engineering assistance
Limits
- 256k context window only
- No vision support in this version
- License is other, not Apache 2.0
Best for
- Local code assistant on RTX 4090
- Agentic coding workflows
- On‑device LLM deployment
Who it’s for. Developers and teams needing a lightweight, instruction‑oriented LLM for software engineering tasks. Suitable for local deployment on GPUs with 8 GB VRAM or more, or on‑device use with 32 GB RAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → |
The Q4_K_M quantization file is 14.33 GB and requires approximately 16.2 GB of VRAM at 8 k context. For 8 GB VRAM, a smaller quantization would be needed, but none is available in the file list. For 16 GB VRAM, Q4_K_M is suitable.
What GPU do you need for Mistralai Devstral Small 2 24B Instruct 2512?
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 Q4_K_M (14.3 GB file, about 16.2 GB in use).
Which Mistralai Devstral Small 2 24B Instruct 2512 quant should you choose?
Q4_K_M is the usual starting point for Mistralai Devstral Small 2 24B Instruct 2512: it balances file size and quality well. Here it is a 14.3 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Mistralai Devstral Small 2 24B Instruct 2512
How much VRAM does Mistralai Devstral Small 2 24B Instruct 2512 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 2 24B Instruct 2512 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 2 24B Instruct 2512 GGUF?
It depends on the quant: Q4_K_M is 14.3 GB.
What context length does Mistralai Devstral Small 2 24B Instruct 2512 support?
The GGUF header lists a trained context length of 393,216 tokens (384K). 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 2 24B Instruct 2512 GGUF?
The files are on Hugging Face in the sigmanih/mistralai-Devstral-Small-2-24B-Instruct-2512-GGUF-Q4_K_M 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 2 24B Instruct 2512 use?
Hugging Face lists the license as other. 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 this model on 8 GB VRAM?
The Q4_K_M quantized model requires about 16.2 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.
What context length does this model support?
It supports a 256k token context window.
Is this model licensed for commercial use?
The license is listed as other; consult the license details for commercial use.