magistral-small-2509 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 4 quants, from 14.3 GB (Q4_K_M) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
24B parameter Mistral model with advanced reasoning and vision support
Magistral Small 1.2 is a 24 billion‑parameter Llama‑style model focused on reasoning. It supports a 128k context window and includes vision capabilities. The model is released under Apache 2.0 and can be run locally on a single RTX 4090 or a 32 GB MacBook after quantization.
Good at
- Long‑chain reasoning
- Multimodal text and image understanding
- High‑quality formatting in LaTeX and Markdown
Limits
- Large context may degrade past 40k tokens
- Requires quantization for local deployment
- Vision encoder not included in GGUF files
Best for
- Complex reasoning tasks
- Multilingual document analysis
- Chatbots needing structured responses
Who it’s for. Developers building local LLM applications that need robust reasoning and multimodal input. The model is suitable for research and commercial use under the Apache 2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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 → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (14.33 GB file, ~16.2 GB VRAM at 8k context). For 12 GB VRAM, Q5_K_M (16.76 GB file, ~18.6 GB VRAM). If you have 24 GB VRAM, Q8_0 (25.06 GB file, ~26.9 GB VRAM) offers higher precision. BF16 requires ~49 GB VRAM and is not recommended for most local setups.
What GPU do you need for magistral-small-2509?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (16.8 GB file, about 18.6 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 magistral-small-2509 quant should you choose?
Q4_K_M is the usual starting point for magistral-small-2509: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about magistral-small-2509
How much VRAM does magistral-small-2509 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 magistral-small-2509 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of magistral-small-2509 GGUF?
It depends on the quant: Q4_K_M is 14.3 GB, Q5_K_M is 16.8 GB, Q8_0 is 25.1 GB, BF16 is 47.2 GB.
What context length does magistral-small-2509 support?
The GGUF header lists a trained context length of 40,960 tokens (40K). 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 magistral-small-2509 GGUF?
The files are on Hugging Face in the mistralai/Magistral-Small-2509-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 magistral-small-2509 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 Magistral Small 1.2 on an RTX 4090?
Yes, after quantization the model fits within the 24 GB VRAM of an RTX 4090.
Does the GGUF file include the vision encoder?
No, the vision encoder is not part of the GGUF files; only the text model is provided.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.