MI

Mistral Small 4 119B 2603

MistralGGUF by bartowskiUpdated 2026-03-22
Download on Hugging Face
Parameters119B
Context1024K
Layers36
Architecturemistral4
Smallest quant0.1 GB
Quick answer

Mistral Small 4 119B 2603 needs about 73.5 GB of memory at Q4_K_M (a 72.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 28 quants, from 0.1 GB to 126.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

Mistral Small 4 119B 2603 – a multimodal, 256k context hybrid instruction and reasoning model

Mistral Small 4 119B 2603 is a 119‑billion‑parameter model that supports text and image input. It offers instruction, reasoning, and function‑calling capabilities with a 256k context window. The model is licensed under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Multimodal text and image processing
  • Large context reasoning
  • Fast inference with optimized quantizations

Limits

  • Requires 256k context support
  • Large memory footprint for high‑precision quants
  • No native vision support in some runtimes

Best for

  • Chatbots needing long context
  • Vision‑enabled content analysis
  • Complex reasoning tasks

Who it’s for. Developers building advanced chat or agent systems that need both instruction following and reasoning. The model is suitable for applications that require large context windows and multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.0 GB
Fits Get file →
IQ1_S26.9 GB 27.7 GB
Too big Get file →
IQ1_M29.5 GB 30.4 GB
Too big Get file →
IQ2_XXS33.7 GB 34.5 GB
Too big Get file →
IQ2_XS37.0 GB 37.9 GB
Too big Get file →
IQ2_S38.1 GB 39.0 GB
Too big Get file →
IQ2_M41.6 GB 42.5 GB
Too big Get file →
Q2_K42.1 GB 42.9 GB
Too big Get file →
Q2_K_L42.6 GB 43.4 GB
Too big Get file →
IQ3_XXS49.9 GB 50.7 GB
Too big Get file →
IQ3_XS51.8 GB (2 parts) 52.6 GB
Too big Get file →
Q3_K_S52.0 GB (2 parts) 52.8 GB
Too big Get file →
Q3_K_M54.6 GB (2 parts) 55.4 GB
Too big Get file →
Q3_K_L56.9 GB (2 parts) 57.7 GB
Too big Get file →
IQ3_M57.0 GB (2 parts) 57.8 GB
Too big Get file →
Q3_K_XL57.4 GB (2 parts) 58.2 GB
Too big Get file →
IQ4_XS63.8 GB (2 parts) 64.6 GB
Too big Get file →
IQ4_NL67.5 GB (2 parts) 68.3 GB
Too big Get file →
Q4_067.7 GB (2 parts) 68.5 GB
Too big Get file →
Q4_K_S69.9 GB (2 parts) 70.7 GB
Too big Get file →
Q4_K_M72.6 GB (2 parts) 73.5 GB
Too big Get file →
Q4_K_L73.0 GB (2 parts) 73.9 GB
Too big Get file →
Q5_K_S82.2 GB (3 parts) 83.1 GB
Too big Get file →
Q5_K_M85.0 GB (3 parts) 85.9 GB
Too big Get file →
Q5_K_L85.4 GB (3 parts) 86.2 GB
Too big Get file →
Q6_K102.8 GB (3 parts) 103.6 GB
Too big Get file →
Q6_K_L103.1 GB (3 parts) 103.9 GB
Too big Get file →
Q8_0126.5 GB (4 parts) 127.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (27.7 GB memory at 8k context) or Q4_0 (68.5 GB). For 16 GB VRAM, IQ2_XS (37.9 GB) or Q4_K_S (70.7 GB) are suitable. Higher precision quants such as Q6_K or Q8_0 require 100 GB+ VRAM and are not recommended for typical consumer hardware.

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

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: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_M (29.5 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K_L (42.6 GB file, about 43.4 GB in use).

Which Mistral Small 4 119B 2603 quant should you choose?

Q4_K_M is the usual starting point for Mistral Small 4 119B 2603: it balances file size and quality well. Here it is a 72.6 GB file.

The Q8_0 file is 126.5 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral4
Parameters119B (approximate, mixture of experts)
Layers36
Trained context1,048,576 tokens
KV cache (fp16)41 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseapache-2.0
Downloads (HF)16,746
Last updated2026-03-22

Frequently asked questions about Mistral Small 4 119B 2603

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

About 73.5 GB at Q4_K_M with an 8K context window. That is the 72.6 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 Mistral Small 4 119B 2603 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.1 GB, IQ1_S is 26.9 GB, IQ1_M is 29.5 GB, IQ2_XXS is 33.7 GB, IQ2_XS is 37.0 GB, IQ2_S is 38.1 GB and 22 more.

What context length does Mistral Small 4 119B 2603 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 GGUF?

The files are on Hugging Face in the bartowski/mistralai_Mistral-Small-4-119B-2603-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 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 Mistral Small 4 119B 2603 on 8 GB VRAM?

Only low‑precision quants such as IQ1_S or Q4_0 can fit, requiring about 27–68 GB of VRAM at 8k context, so 8 GB is insufficient.

Does the model support vision?

Yes, it accepts image input and provides text output, but some runtimes may need additional configuration.

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 Mistral-Small-4-119B-2603

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other large models

All large models →