Mistral Small 119B 2603 ik needs about 68.1 GB of memory at its main file (a 67.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 67.2 GB to 82.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
Mistral Small 119B 2603 ik – a multimodal, MoE LLM with 256k context
Mistral Small 119B 2603 ik is a 119B‑parameter model that supports text and image input. It uses a mixture‑of‑experts architecture with 128 experts, 4 active per token, and offers both instruction and reasoning modes. The model is licensed under Apache‑2.0.
Good at
- Multimodal text and image tasks
- Large‑context reasoning
- Function calling and JSON output
Limits
- Requires >68 GB VRAM for 8k context
- No native vision support in GGUF
- Large file size limits deployment on consumer GPUs
Best for
- Complex reasoning with large context
- Multimodal content analysis
- Agentic workflows with function calls
Who it’s for. Developers building advanced AI assistants that need both vision and deep reasoning. Researchers requiring a large‑context, multimodal LLM for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 67.2 GB | 68.1 GB | Too big | Get file → | |
| — | 82.0 GB | 82.8 GB | Too big | Get file → |
The available GGUF files are 67.24 GB and 81.96 GB, both with unknown quant. For a system with 70 GB VRAM, the 67.24 GB file is the only viable option. If you have 90 GB VRAM, the 81.96 GB file can be used. Memory estimates are approximate and depend on context length.
What GPU do you need for Mistral Small 119B 2603 ik?
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
Source
Frequently asked questions about Mistral Small 119B 2603 ik
How much VRAM does Mistral Small 119B 2603 ik need?
About 68.1 GB at its main file with an 8K context window. That is the 67.2 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 119B 2603 ik on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 68.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral Small 119B 2603 ik GGUF?
It depends on the quant: file is 67.2 GB, file is 82.0 GB.
What context length does Mistral Small 119B 2603 ik 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 119B 2603 ik GGUF?
The files are on Hugging Face in the AlexanderKyng/Mistral-Small-119B-2603-ik-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 119B 2603 ik 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?
No. The model requires over 68 GB VRAM at 8k context, far beyond 8 GB.
Does the GGUF version support vision?
The GGUF files are text‑only; vision requires the original .mmproj file.
What license applies to this model?
Apache‑2.0, allowing commercial and non‑commercial use.