MI

Devstral Small 2507 DASHQ Q2

MistralGGUF by jkim96Updated 2026-10-09
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant6.8 GB
Quick answer

Devstral Small 2507 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 2507 DASHQ Q2 – 23.6B param, 128k context, coding agent

Devstral Small 2507 DASHQ Q2 is a 23.6 billion‑parameter LLM fine‑tuned for agentic coding tasks. It supports a 128k token context window and is released under Apache 2.0. The model is text‑only, with no vision encoder.

Good at

  • Agentic coding
  • Tool usage
  • Function calling

Limits

  • No vision support
  • Requires 128k context for full capability
  • No mixture of experts

Best for

  • Local software‑engineering agents
  • Codebase exploration
  • Multi‑file editing

Who it’s for. Developers and researchers needing a lightweight, open‑source LLM for coding tasks. The model runs on a single RTX 4090 or a Mac with 32 GB RAM, making it suitable for local deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS6.8 GB 8.6 GB
Too big Get file →
IQ2_XS7.7 GB 9.5 GB
Too big Get file →
IQ2_M8.3 GB 10.1 GB
Too big Get file →
Q2_K_XL9.1 GB 11.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (6.76 GB file, 8.6 GB memory at 8k context). For 10 GB VRAM, IQ2_XS (7.68 GB, 9.5 GB). For 12 GB VRAM, IQ2_M (8.25 GB, 10.1 GB). For 16 GB VRAM, Q2_K_XL (9.15 GB, 11 GB). Memory estimates are approximate.

What GPU do you need for Devstral Small 2507 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 2507 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

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byjkim96
FamilyMistral
Licenseapache-2.0
Downloads (HF)667
Last updated2026-10-09

Frequently asked questions about Devstral Small 2507 DASHQ Q2

How much VRAM does Devstral Small 2507 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 2507 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 2507 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 2507 DASHQ Q2 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 Devstral Small 2507 DASHQ Q2 GGUF?

The files are on Hugging Face in the jkim96/Devstral-Small-2507-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 2507 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 2507 on an RTX 4090 with 8 GB VRAM?

Yes, the IQ2_XXS quantized file is 6.76 GB and requires about 8.6 GB VRAM at 8k context, fitting an RTX 4090.

Does this model support vision or image input?

No, the model is text‑only; the vision encoder was removed during fine‑tuning.

What license applies to this model?

It is released under the Apache 2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of Devstral-Small-2507

Similar models

Browse all →

More from jkim96

All by jkim96 →

More Mistral models

All Mistral →

Other medium models

All medium models →