MI

Magistral Small 2509 Vision

MistralGGUF by EnlistedGhostUpdated 2026-07-11
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturemistral3
Smallest quant8.7 GB
Quick answer

Magistral Small 2509 Vision needs about 14.5 GB of memory at Q4_K_M (a 12.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 20 quants, from 8.7 GB (Q2_K_M) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Magistral Small 2509 Vision – 23.6B parameter multimodal model

Magistral Small 2509 Vision is a 23.6 billion parameter model based on the Mistral3 architecture. It supports text and vision tasks and is released under the apache‑2.0 license. The model was re‑configured with a custom chat‑template and system‑prompt.

Good at

  • Vision‑enabled reasoning
  • Tool use
  • Multimodal text generation

Limits

  • Requires 8 k context for estimates
  • No vision support in older quant files
  • Large VRAM needed for higher quants

Best for

  • Image captioning
  • Multimodal chatbots
  • Vision‑based data analysis

Who it’s for. Developers building multimodal applications who need a compact yet capable model. The model is ready to use with Huggingface SafeTensors, Pipeline, or vLLM without additional configuration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_M8.7 GB 10.5 GB
Too big Get file →
Q2_K_S9.0 GB 10.9 GB
Too big Get file →
Q2_K9.2 GB 11.1 GB
Too big Get file →
Q3_K_S10.7 GB 12.5 GB
Too big Get file →
Q2_K_L10.8 GB 12.6 GB
Too big Get file →
Q3_K_M11.2 GB 13.0 GB
Too big Get file →
Q3_K_L12.1 GB 13.9 GB
Too big Get file →
Q4_K_M12.6 GB 14.5 GB
Too big Get file →
Q3_K_XL13.3 GB 15.2 GB
Too big Get file →
Q4_K_S13.5 GB 15.4 GB
Too big Get file →
Q4_K_XL14.8 GB 16.7 GB
Too big Get file →
Q5_K_XL15.8 GB 17.6 GB
Too big Get file →
Q5_K_S16.4 GB 18.2 GB
Too big Get file →
Q5_K_M16.7 GB 18.6 GB
Too big Get file →
Q6_K19.3 GB 21.2 GB
Too big Get file →
Q6_K_M19.7 GB 21.5 GB
Too big Get file →
Q6_K_XL20.9 GB 22.8 GB
Too big Get file →
Q8_025.1 GB 26.9 GB
Too big Get file →
Q6_K_L27.7 GB 29.6 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K_M (file size 8.69 GB, estimated 10.5 GB memory). For 12 GB VRAM, Q3_K_M (file size 11.17 GB, estimated 13 GB memory). For 16 GB VRAM, Q4_K_M (file size 12.62 GB, estimated 14.5 GB memory). These estimates are approximate.

What GPU do you need for Magistral Small 2509 Vision?

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 (9.2 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_XL (20.9 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (27.7 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K_L (27.7 GB file, about 29.6 GB in use).

Which Magistral Small 2509 Vision quant should you choose?

Q4_K_M is the usual starting point for Magistral Small 2509 Vision: it balances file size and quality well. Here it is a 12.6 GB file.

The Q8_0 file is 25.1 GB, about 2.0 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 Q2_K_M at 8.7 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

Architecturemistral3
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byEnlistedGhost
FamilyMistral
Licenseapache-2.0
Downloads (HF)644
Last updated2026-07-11

Frequently asked questions about Magistral Small 2509 Vision

How much VRAM does Magistral Small 2509 Vision need?

About 14.5 GB at Q4_K_M with an 8K context window. That is the 12.6 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 Vision on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Magistral Small 2509 Vision GGUF?

It depends on the quant: Q2_K_M is 8.7 GB, Q2_K_S is 9.0 GB, Q2_K is 9.2 GB, Q3_K_S is 10.7 GB, Q2_K_L is 10.8 GB, Q3_K_M is 11.2 GB and 14 more.

What context length does Magistral Small 2509 Vision 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 Magistral Small 2509 Vision GGUF?

The files are on Hugging Face in the EnlistedGhost/Magistral-Small-2509-Vision-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 Vision 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 Q2_K_M quant requires about 10.5 GB memory at 8 k context, which fits within an 8 GB VRAM budget with some overhead.

Does the model support vision tasks?

Yes, the model includes vision functionality and works with the updated projector. It can process images and generate text responses.

What license applies to this model?

The model is released under the apache‑2.0 license, allowing free use and modification.

Other GGUFs of Magistral-Small-2509-Vision

Similar models

Browse all →

More from EnlistedGhost

All by EnlistedGhost →

More Mistral models

All Mistral →

Other medium models

All medium models →