MI

Devstral-Small-2505

MistralGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant5.6 GB
Quick answer

Devstral-Small-2505 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 31 quants, from 5.6 GB (TQ1_0) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Devstral-Small-2505: 23.6B parameter agentic coding model

Devstral-Small-2505 is a 23.6B parameter model fine‑tuned from Mistral‑Small‑3.1. It supports a 128k token context window and is optimized for coding and tool‑using tasks. The model is released under an Apache‑2.0 license.

Good at

  • Agentic coding
  • Tool‑based code editing
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Single‑GPU deployment may need RTX 4090 or 32GB RAM

Best for

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

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 32GB RAM, making it suitable for local deployment and on‑device use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_05.6 GB 7.5 GB
Tight Get file →
IQ1_S6.5 GB 8.4 GB
Too big Get file →
TQ2_06.7 GB 8.5 GB
Too big Get file →
IQ1_M7.0 GB 8.9 GB
Too big Get file →
IQ2_XXS7.4 GB 9.2 GB
Too big Get file →
IQ2_XS8.0 GB 9.8 GB
Too big Get file →
IQ2_S8.2 GB 10.1 GB
Too big Get file →
Q2_K_S8.4 GB 10.2 GB
Too big Get file →
IQ2_M8.7 GB 10.5 GB
Too big Get file →
Q2_K_M9.1 GB 11.0 GB
Too big Get file →
IQ3_XXS9.5 GB 11.4 GB
Too big Get file →
IQ3_XS10.0 GB 11.8 GB
Too big Get file →
IQ3_S10.5 GB 12.3 GB
Too big Get file →
IQ3_M10.6 GB 12.5 GB
Too big Get file →
Q3_K_S10.6 GB 12.5 GB
Too big Get file →
Q3_K_M11.6 GB 13.5 GB
Too big Get file →
IQ4_XS12.8 GB 14.6 GB
Too big Get file →
Q4_013.3 GB 15.1 GB
Too big Get file →
IQ4_NL13.5 GB 15.3 GB
Too big Get file →
Q4_K_S13.8 GB 15.7 GB
Too big Get file →
Q4_K_M14.3 GB 16.2 GB
Too big Get file →
Q4_114.7 GB 16.6 GB
Too big Get file →
Q5_016.2 GB 18.1 GB
Too big Get file →
Q5_K_S16.6 GB 18.4 GB
Too big Get file →
Q5_K_M16.9 GB 18.7 GB
Too big Get file →
Q5_117.7 GB 19.5 GB
Too big Get file →
Q6_K_M19.3 GB 21.2 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →
BF1633.6 GB 35.4 GB
Too big Get file →
F1633.6 GB 35.4 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

For 8GB VRAM, use Q4_K_M (14.34GB file, 16.2GB memory at 8k context). For 12GB VRAM, Q3_K_M (11.64GB file, 13.5GB memory). For 24GB VRAM, Q5_K_M (16.88GB file, 18.7GB memory). Estimates are approximate.

What GPU do you need for Devstral-Small-2505?

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: the best quant that fits is TQ1_0 (5.6 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XS (10.0 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_M (19.3 GB file, about 21.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (33.6 GB file, about 35.4 GB in use).

Which Devstral-Small-2505 quant should you choose?

Q4_K_M is the usual starting point for Devstral-Small-2505: 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.

If memory is tight, the smallest file is TQ1_0 at 5.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

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 byMungert
FamilyMistral
Licenseapache-2.0
Downloads (HF)778
Last updated2025-09-24

Frequently asked questions about Devstral-Small-2505

How much VRAM does Devstral-Small-2505 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-2505 on an 8 GB GPU?

Yes, with TQ1_0: the 5.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Devstral-Small-2505 GGUF?

It depends on the quant: TQ1_0 is 5.6 GB, IQ1_S is 6.5 GB, TQ2_0 is 6.7 GB, IQ1_M is 7.0 GB, IQ2_XXS is 7.4 GB, IQ2_XS is 8.0 GB and 25 more.

What context length does Devstral-Small-2505 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-2505 GGUF?

The files are on Hugging Face in the Mungert/Devstral-Small-2505-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-2505 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-2505 on an RTX 4090?

Yes, the 24GB VRAM of an RTX 4090 can accommodate the Q4_K_M quantization, which requires 16.2GB memory at 8k context.

Does the model support image input?

No, the vision encoder was removed before fine‑tuning, so the model is text‑only.

What license applies to this model?

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

Other GGUFs of Devstral-Small-2505

Similar models

Browse all →

More from Mungert

All by Mungert →

More Mistral models

All Mistral →

Other medium models

All medium models →