Devstral-Small-2-24B-Instruct-2512 needs about 10.0 GB of memory at IQ3_S (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 6.9 GB (IQ2_S) to 11.9 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Devstral Small 2 24B Instruct 2512 – an agentic coding LLM with vision
Devstral Small 2 24B Instruct 2512 is a 23.6 billion‑parameter model fine‑tuned for instruction following and agentic coding. It supports a 256k context window and includes vision capabilities. The model is open‑source under Apache‑2.0.
Good at
- Agentic coding tasks
- Vision‑enabled code analysis
- Instruction‑driven chat
Limits
- No explicit vision projector in GGUF
- Requires 8k context for memory estimates
- No mention of specialized domain tuning
Best for
- Local software engineering assistants
- Multimodal code review tools
- On‑device coding agents
Who it’s for. Developers and teams needing a lightweight, open‑source LLM for software engineering tasks. The model runs on a single RTX 4090 or a Mac with 32 GB RAM, making it suitable for local deployment and on‑device use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 6.9 GB | 8.7 GB | Too big | Get file → | |
| IQ2_S | 7.2 GB | 9.0 GB | Too big | Get file → | |
| IQ3_S | 7.9 GB | 9.7 GB | Too big | Get file → | |
| IQ3_S | 8.2 GB | 10.0 GB | Too big | Get file → | |
| IQ3_S | 8.7 GB | 10.6 GB | Too big | Get file → | |
| IQ3_S | 9.4 GB | 11.2 GB | Too big | Get file → | |
| IQ3_S | 10.2 GB | 12.1 GB | Too big | Get file → | |
| IQ4_XS | 11.9 GB | 13.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S (6.9 GB file, 8.7 GB memory at 8k context). For 12 GB VRAM, IQ3_S (8.72 GB file, 10.6 GB memory) is a good balance. If more VRAM is available, IQ4_XS (11.92 GB file, 13.8 GB memory) offers higher quality.
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: the best quant that fits is IQ3_S (9.4 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (11.9 GB file, about 13.8 GB in use).
Which Devstral-Small-2-24B-Instruct-2512 quant should you choose?
IQ3_S (8.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_S at 6.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 10.0 GB at IQ3_S with an 8K context window. That is the 8.2 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 8.7 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: IQ2_S is 6.9 GB, IQ2_S is 7.2 GB, IQ3_S is 7.9 GB, IQ3_S is 8.2 GB, IQ3_S is 8.7 GB, IQ3_S is 9.4 GB and 2 more.
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 byteshape/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?
Yes, the IQ2_S quantization uses 6.9 GB file size and requires about 8.7 GB VRAM at 8k context, which fits an RTX 4090.
Does the model support vision tasks?
Yes, the model includes vision capabilities and can analyze images when used with a projector file in llama.cpp.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.