Mistral Small 4 119B 2603 Heretic needs about 73.0 GB of memory at Q4_K_M (a 72.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 15 quants, from 0.1 GB to 97.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
Mistral Small 4 119B 2603 Heretic – 119B multimodal LLM with 256k context
Mistral Small 4 119B 2603 Heretic is a 119‑billion‑parameter multimodal model based on the Mistral‑4 architecture. It supports text and image input, offers a large 256k token context window, and is released under Apache‑2.0.
Good at
- Large context reasoning
- Multimodal text‑image tasks
- Native JSON function calling
Limits
- Requires 256k context support
- No built‑in vision model, image input only via prompt
- Large VRAM needed for full precision
Best for
- Complex document summarization
- Multimodal chat assistants
- Agentic task orchestration
Who it’s for. Developers building advanced chat or agent systems that need a large context window and multimodal input. The model is suitable for commercial or research use under the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XXS | 31.2 GB | 32.0 GB | Too big | Get file → | |
| IQ2_XS | 34.8 GB | 35.6 GB | Too big | Get file → | |
| IQ2_S | 35.2 GB | 36.0 GB | Too big | Get file → | |
| Q2_K | 43.4 GB | 44.2 GB | Too big | Get file → | |
| IQ3_XXS | 45.8 GB | 46.7 GB | Too big | Get file → | |
| IQ3_XS | 48.7 GB | 49.5 GB | Too big | Get file → | |
| Q3_K_S | 51.4 GB | 52.2 GB | Too big | Get file → | |
| Q3_K_M | 56.9 GB | 57.8 GB | Too big | Get file → | |
| Q3_K_L | 61.6 GB | 62.4 GB | Too big | Get file → | |
| IQ4_XS | 63.4 GB | 64.3 GB | Too big | Get file → | |
| IQ4_NL | 67.1 GB | 68.0 GB | Too big | Get file → | |
| Q4_K_M | 72.2 GB | 73.0 GB | Too big | Get file → | |
| Q5_K_M | 84.5 GB | 85.4 GB | Too big | Get file → | |
| Q6_K | 97.7 GB | 98.5 GB | Too big | Get file → |
For 8 GB VRAM use IQ2_XXS (31 GB file, ~32 GB VRAM). With 16 GB VRAM IQ3_XS (48.7 GB file, ~49.5 GB VRAM) is suitable. For 32 GB VRAM, Q4_K_M (72.2 GB file, ~73 GB VRAM) offers a good balance of size and performance. Estimates are approximate.
What GPU do you need for Mistral Small 4 119B 2603 Heretic?
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 IQ2_XXS (31.2 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_XXS (45.8 GB file, about 46.7 GB in use).
Which Mistral Small 4 119B 2603 Heretic quant should you choose?
Q4_K_M is the usual starting point for Mistral Small 4 119B 2603 Heretic: it balances file size and quality well. Here it is a 72.2 GB file.
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
Frequently asked questions about Mistral Small 4 119B 2603 Heretic
How much VRAM does Mistral Small 4 119B 2603 Heretic need?
About 73.0 GB at Q4_K_M with an 8K context window. That is the 72.2 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 4 119B 2603 Heretic 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 Heretic GGUF?
It depends on the quant: file is 0.1 GB, IQ2_XXS is 31.2 GB, IQ2_XS is 34.8 GB, IQ2_S is 35.2 GB, Q2_K is 43.4 GB, IQ3_XXS is 45.8 GB and 9 more.
What context length does Mistral Small 4 119B 2603 Heretic 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 Heretic GGUF?
The files are on Hugging Face in the Rioky/Mistral-Small-4-119B-2603-heretic-i1-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 Heretic 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 Heretic on 8 GB VRAM?
No, the smallest quantization requires at least 32 GB VRAM. 8 GB VRAM is insufficient for any available quantization.
Does the model support vision tasks?
Yes, it accepts image input and produces text output, but it does not include a separate vision backbone.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.