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. 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 2 24B Instruct 2512 – a 24 billion‑parameter agentic coding model
Devstral Small 2 24B Instruct 2512 is a 24 billion‑parameter Mistral3 model fine‑tuned in FP8 for instruction following. It supports coding, tools, and vision tasks and offers a 256k context window. The model is licensed under Apache 2.0.
Good at
- Agentic coding tasks
- Tool‑based code exploration
- Multimodal vision analysis
Limits
- 256k context window only
- No native vision support without projector
- Requires 8 k context for memory estimates
Best for
- Local code assistant deployment
- Software engineering agent workflows
- Multimodal code documentation
Who it’s for. Developers and enterprises needing a lightweight, instruction‑driven LLM for software engineering. The model runs on a single RTX 4090 or a Mac 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 → | |
| 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 → |
For 8 GB VRAM, use Q4_K_M (14.33 GB file, 16.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (16.76 GB file, 18.6 GB memory). For 24 GB VRAM, Q8_0 (25.05 GB file, 26.9 GB memory).
What GPU do you need for 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 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).
Which Devstral Small 2 24B Instruct 2512 quant should you choose?
Q4_K_M is the usual starting point for Devstral Small 2 24B Instruct 2512: 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
Frequently asked questions about Devstral Small 2 24B Instruct 2512
How much VRAM does 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 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 Devstral Small 2 24B Instruct 2512 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.
What context length does 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 Devstral Small 2 24B Instruct 2512 GGUF?
The files are on Hugging Face in the backpack-run/Devstral-Small-2-24B-Instruct-2512-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 2 24B Instruct 2512 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 2 on an RTX 4090 with 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 16.2 GB memory at 8 k context, which exceeds 8 GB VRAM, so it is not feasible.
Does the model support image input?
Yes, but a multimodal projector is required and the image projector must be used with one of the language‑model GGUF files.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use and modification.