Mistral-Small-4-119B-2603 needs about 86.0 GB of memory at its main file (a 85.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 52.9 GB to 91.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
Mistral‑Small‑4‑119B‑2603: a multimodal MoE model with 256k context
Mistral‑Small‑4‑119B‑2603 is a 119‑billion‑parameter Mixture‑of‑Experts model. It supports text and image input, offers instruction and reasoning modes, and runs under an Apache‑2.0 license. The model can handle up to 1 M context tokens and includes 128 experts with 4 active per token.
Good at
- Multimodal text‑image tasks
- Large‑context reasoning
- Fast inference with MoE
Limits
- Requires high VRAM (≈53 GB at 8 k context)
- No native vision support in GGUF files
- Large context window limits practical usage
Best for
- Chatbots needing long context
- Vision‑enabled content analysis
- Complex reasoning workflows
Who it’s for. Developers building AI assistants that need both instruction following and advanced reasoning. The model is suitable for research and production use under the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 52.9 GB | 53.7 GB | Too big | Get file → | |
| — | 66.2 GB | 67.0 GB | Too big | Get file → | |
| — | 66.2 GB | 67.0 GB | Too big | Get file → | |
| — | 85.1 GB | 86.0 GB | Too big | Get file → | |
| — | 85.1 GB | 86.0 GB | Too big | Get file → | |
| — | 91.5 GB | 92.3 GB | Too big | Get file → | |
| — | 91.5 GB | 92.3 GB | Too big | Get file → |
For 8 GB VRAM use the smallest available quant, but none are provided. With 16 GB VRAM the 52.89 GB file is still too large. The 66.15 GB and 85.12 GB files require 67 GB and 86 GB VRAM respectively. Memory estimates are approximate.
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: 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.
Which Mistral-Small-4-119B-2603 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 52.9 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
Source
Frequently asked questions about Mistral-Small-4-119B-2603
How much VRAM does Mistral-Small-4-119B-2603 need?
About 86.0 GB at its main file with an 8K context window. That is the 85.1 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?
Not at an 8K context. The smallest file needs about 53.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral-Small-4-119B-2603 GGUF?
It depends on the quant: file is 52.9 GB, file is 66.2 GB, file is 66.2 GB, file is 85.1 GB, file is 85.1 GB, file is 91.5 GB and 1 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 mudler/Mistral-Small-4-119B-2603-APEX-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?
No. The smallest GGUF file requires about 53 GB of VRAM at 8 k context.
Does this model support vision?
Yes, it includes a Pixtral encoder for image input and text output.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.