Devstral Small 2505 Deepseek V3.2 Speciale Distill 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 14 quants, from 7.2 GB (IQ2_XS) to 47.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Devstral Small 2505 Deepseek V3.2 Speciale Distill – a 23.6B llama model fine‑tuned for coding, reasoning and tools.
This 23.6B llama model is fine‑tuned from unsloth/Devstral‑Small‑2505 on DeepSeek v3.2 Speciale datasets. It supports coding, reasoning and tool usage. The model is licensed under apache‑2.0 and trained with a 131072 token context.
Good at
- Coding
- Reasoning
- Tool usage
Limits
- No vision support
- Large memory requirement for higher quants
- No mixture of experts
Best for
- Code generation
- Math problem solving
- Chat with tool integration
Who it’s for. Developers and researchers who need a versatile language model for code, math, and tool‑based tasks. The model is suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 7.2 GB | 9.0 GB | Too big | Get file → | |
| IQ2_M | 8.1 GB | 10.0 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 13.3 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| IQ4_NL | 13.5 GB | 15.3 GB | Too big | Get file → | |
| 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 → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → | |
| F16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (7.21 GB file, 9 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (14.33 GB file, 16.2 GB memory) is a good balance. For 24 GB VRAM, Q5_K_M (16.76 GB file, 18.6 GB memory) offers higher quality.
What GPU do you need for Devstral Small 2505 Deepseek V3.2 Speciale Distill?
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_XS (9.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_NL (13.5 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (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 Q8_0 (25.1 GB file, about 26.9 GB in use).
Which Devstral Small 2505 Deepseek V3.2 Speciale Distill quant should you choose?
Q4_K_M is the usual starting point for Devstral Small 2505 Deepseek V3.2 Speciale Distill: 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 IQ2_XS at 7.2 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 2505 Deepseek V3.2 Speciale Distill
How much VRAM does Devstral Small 2505 Deepseek V3.2 Speciale Distill 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 Deepseek V3.2 Speciale Distill on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Devstral Small 2505 Deepseek V3.2 Speciale Distill GGUF?
It depends on the quant: IQ2_XS is 7.2 GB, IQ2_M is 8.1 GB, IQ3_XS is 9.9 GB, Q3_K_S is 10.4 GB, IQ3_M is 10.7 GB, Q3_K_M is 11.5 GB and 8 more.
What context length does Devstral Small 2505 Deepseek V3.2 Speciale Distill 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 Deepseek V3.2 Speciale Distill GGUF?
The files are on Hugging Face in the TeichAI/Devstral-Small-2505-Deepseek-V3.2-Speciale-Distill-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 Deepseek V3.2 Speciale Distill 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 this model on 8 GB VRAM?
Yes, the IQ2_XS quant uses 7.21 GB file size and requires about 9 GB memory at 8k context.
Does this model support vision tasks?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.