MI

Mistral Small 4 119B 2603 NVFP4

MistralGGUF by FedericoFBUpdated 2026-09-21
Download on Hugging Face
Parameters119B
Context1024K
Layers36
Architecturedeepseek2
Smallest quant70.0 GB
Quick answer

Mistral Small 4 119B 2603 NVFP4 needs about 70.8 GB of memory at its main file (a 70.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

Mistral Small 4 119B 2603 NVFP4 – a multimodal, Mixture‑of‑Experts LLM

Mistral Small 4 119B 2603 NVFP4 is a 119‑billion‑parameter hybrid model that supports text and image input. It offers instruction, reasoning, and agentic capabilities with a 256k context window.

Good at

  • Multimodal text‑image tasks
  • Large‑context reasoning
  • Fast inference with MoE

Limits

  • Requires 70.8 GB VRAM at 8k context
  • CC‑BY‑NC‑4.0 license limits commercial use
  • No native vision output beyond analysis

Best for

  • Chatbots needing image analysis
  • Long‑form document reasoning
  • Agentic workflows with function calls

Who it’s for. Developers building advanced conversational agents that need both vision and large‑context reasoning. The model is suitable for research and non‑commercial applications under the CC‑BY‑NC‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—70.0 GB 70.8 GB
Too big Get file →

The only available GGUF file is the unknown‑quant version, 69.99 GB in size. It requires approximately 70.8 GB VRAM at 8k context. For lower memory budgets, a different quantization would be needed, but none is listed.

What GPU do you need for Mistral Small 4 119B 2603 NVFP4?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters119B (approximate, mixture of experts)
Layers36
Trained context1,048,576 tokens
KV cache (fp16)41 KB per token

Source

Quantized byFedericoFB
FamilyMistral
Downloads (HF)1,430
Last updated2026-09-21

Frequently asked questions about Mistral Small 4 119B 2603 NVFP4

How much VRAM does Mistral Small 4 119B 2603 NVFP4 need?

About 70.8 GB at its main file with an 8K context window. That is the 70.0 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 Mistral Small 4 119B 2603 NVFP4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 70.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Small 4 119B 2603 NVFP4 GGUF?

It depends on the quant: file is 70.0 GB.

What context length does Mistral Small 4 119B 2603 NVFP4 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.4 GB at 32K.

Where can I download Mistral Small 4 119B 2603 NVFP4 GGUF?

The files are on Hugging Face in the FedericoFB/Mistral-Small-4-119B-2603-NVFP4-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 Mistral Small 4 119B 2603 NVFP4 use?

Hugging Face lists the license as cc-by-nc-4.0. 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?

No. The model needs about 70.8 GB VRAM at 8k context, far beyond 8 GB.

Does it support vision?

Yes. It accepts image input and provides analysis, but outputs only text.

Is it free for commercial use?

No. The CC‑BY‑NC‑4.0 license restricts commercial use.

Similar models

Browse all →

More from FedericoFB

All by FedericoFB →

More Mistral models

All Mistral →

Other large models

All large models →