Devstral Small 2 24B Instruct 2512 DASHQ Q2 needs about 9.5 GB of memory at IQ2_XS (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.8 GB (IQ2_XXS) to 9.1 GB (Q2_K_XL). 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 Mistral3 model fine‑tuned for instruction following and software engineering tasks. It supports a 256k context window and is released under Apache‑2.0. The model excels at using tools to explore codebases and edit multiple files.
Good at
- Agentic coding tasks
- Tool‑based code exploration
- Instruction‑driven chat
Limits
- No vision support in GGUF
- Large context window requires high VRAM
- Requires recent llama.cpp build
Best for
- Local code assistant
- Agentic software engineering workflows
- Instruction‑based debugging
Who it’s for. Developers and teams needing a lightweight, open‑source LLM for local deployment. The model runs on a single RTX 4090 or a Mac with 32 GB RAM, making it suitable for on‑device use and enterprise code‑assistant solutions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 6.8 GB | 8.6 GB | Too big | Get file → | |
| IQ2_XS | 7.7 GB | 9.5 GB | Too big | Get file → | |
| IQ2_M | 8.3 GB | 10.1 GB | Too big | Get file → | |
| Q2_K_XL | 9.1 GB | 11.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (file size 6.76 GB, estimated 8.6 GB memory at 8 k context). If more VRAM is available, IQ2_XS (7.68 GB, 9.5 GB) or IQ2_M (8.25 GB, 10.1 GB) can be used. The Q2_K_XL quant (9.15 GB, 11 GB) offers the highest quality but needs more memory.
What GPU do you need for Devstral Small 2 24B Instruct 2512 DASHQ Q2?
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 Q2_K_XL (9.1 GB file, about 11.0 GB in use).
Which Devstral Small 2 24B Instruct 2512 DASHQ Q2 quant should you choose?
IQ2_XS (7.7 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 6.8 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 DASHQ Q2
How much VRAM does Devstral Small 2 24B Instruct 2512 DASHQ Q2 need?
About 9.5 GB at IQ2_XS with an 8K context window. That is the 7.7 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 DASHQ Q2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Devstral Small 2 24B Instruct 2512 DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 6.8 GB, IQ2_XS is 7.7 GB, IQ2_M is 8.3 GB, Q2_K_XL is 9.1 GB.
What context length does Devstral Small 2 24B Instruct 2512 DASHQ Q2 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 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/Devstral-Small-2-24B-Instruct-2512-DASHQ-Q2-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 DASHQ Q2 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, using the IQ2_XXS quant file will fit within the 8 GB VRAM limit with an estimated 8.6 GB memory usage at 8 k context.
Does the GGUF version include vision capabilities?
No, the GGUF files contain only text; the vision tower is omitted.
What license applies to the model?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.