Mistral Medium 3.5 128B needs about 81.9 GB of memory at Q4_K_M (a 78.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 29 quants, from 0.0 GB to 132.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
Mistral Medium 3.5 128B – dense 128B model with 256k context and vision support
Mistral Medium 3.5 128B is a dense 128B model with a 256k context window. It handles instruction-following, reasoning, coding, and vision in a single set of weights. The model supports multimodal input and function calling.
Good at
- Instruction following
- Reasoning with configurable effort
- Vision analysis
Limits
- Large context requires high memory
- No explicit vision output format
- License is Modified MIT with revenue restrictions
Best for
- Chatbots needing deep context
- Agentic workflows with function calls
- Vision‑enabled content analysis
Who it’s for. Developers building chat or agent applications that require large context and multimodal input. The model is suitable for both commercial and non‑commercial use under a Modified MIT license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.5 GB | Fits | Get file → | |
| IQ1_S | 35.3 GB | 38.8 GB | Too big | Get file → | |
| IQ1_M | 37.3 GB | 40.7 GB | Too big | Get file → | |
| IQ2_XXS | 40.4 GB | 43.9 GB | Too big | Get file → | |
| IQ2_XS | 43.4 GB | 46.8 GB | Too big | Get file → | |
| IQ2_S | 46.1 GB | 49.5 GB | Too big | Get file → | |
| IQ2_M | 48.6 GB | 52.1 GB | Too big | Get file → | |
| Q2_K | 49.9 GB | 53.3 GB | Too big | Get file → | |
| Q2_K_L | 51.4 GB (2 parts) | 54.9 GB | Too big | Get file → | |
| IQ3_XXS | 52.2 GB (2 parts) | 55.6 GB | Too big | Get file → | |
| IQ3_XS | 54.9 GB (2 parts) | 58.4 GB | Too big | Get file → | |
| Q3_K_S | 57.0 GB (2 parts) | 60.4 GB | Too big | Get file → | |
| IQ3_M | 59.5 GB (2 parts) | 63.0 GB | Too big | Get file → | |
| Q3_K_M | 63.3 GB (2 parts) | 66.7 GB | Too big | Get file → | |
| Q3_K_L | 67.0 GB (2 parts) | 70.5 GB | Too big | Get file → | |
| Q3_K_XL | 68.4 GB (2 parts) | 71.9 GB | Too big | Get file → | |
| IQ4_XS | 69.1 GB (2 parts) | 72.6 GB | Too big | Get file → | |
| Q4_0 | 72.7 GB (2 parts) | 76.2 GB | Too big | Get file → | |
| IQ4_NL | 72.8 GB (2 parts) | 76.2 GB | Too big | Get file → | |
| Q4_K_S | 73.0 GB (2 parts) | 76.5 GB | Too big | Get file → | |
| Q4_K_M | 78.4 GB (2 parts) | 81.9 GB | Too big | Get file → | |
| Q4_K_L | 79.6 GB (2 parts) | 83.1 GB | Too big | Get file → | |
| Q4_1 | 79.8 GB (2 parts) | 83.2 GB | Too big | Get file → | |
| Q5_K_S | 87.1 GB (3 parts) | 90.5 GB | Too big | Get file → | |
| Q5_K_M | 91.1 GB (3 parts) | 94.6 GB | Too big | Get file → | |
| Q5_K_L | 92.1 GB (3 parts) | 95.6 GB | Too big | Get file → | |
| Q6_K | 107.8 GB (3 parts) | 111.3 GB | Too big | Get file → | |
| Q6_K_L | 108.6 GB (3 parts) | 112.0 GB | Too big | Get file → | |
| Q8_0 | 132.9 GB (4 parts) | 136.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 72.71 GB, memory 76.2 GB at 8k context). For 16 GB VRAM, Q5_K_S (file size 87.07 GB, memory 90.5 GB) or Q4_K_M (file size 78.41 GB, memory 81.9 GB) are suitable. For 32 GB VRAM, Q6_K (file size 107.8 GB, memory 111.3 GB) or Q6_K_L (file size 108.58 GB, memory 112 GB) provide higher quality.
What GPU do you need for Mistral Medium 3.5 128B?
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 (0.0 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_XS (43.4 GB file, about 46.8 GB in use).
Which Mistral Medium 3.5 128B quant should you choose?
Q4_K_M is the usual starting point for Mistral Medium 3.5 128B: it balances file size and quality well. Here it is a 78.4 GB file.
The Q8_0 file is 132.9 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 0.0 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 Medium 3.5 128B
How much VRAM does Mistral Medium 3.5 128B need?
About 81.9 GB at Q4_K_M with an 8K context window. That is the 78.4 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 Medium 3.5 128B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral Medium 3.5 128B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 35.3 GB, IQ1_M is 37.3 GB, IQ2_XXS is 40.4 GB, IQ2_XS is 43.4 GB, IQ2_S is 46.1 GB and 23 more.
What context length does Mistral Medium 3.5 128B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.
Where can I download Mistral Medium 3.5 128B GGUF?
The files are on Hugging Face in the bartowski/mistralai_Mistral-Medium-3.5-128B-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 Medium 3.5 128B use?
Hugging Face lists the license as other. 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 Medium 3.5 128B on 8 GB VRAM?
The Q4_0 quant requires approximately 76.2 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Does the model support image input?
Yes, the model includes a vision encoder trained from scratch for variable image sizes.
What license applies to this model?
The model is released under a Modified MIT License, allowing commercial use with revenue exceptions.