mistralai.Mistral Medium 3.5 128B needs about 78.3 GB of memory at Q4_K_M (a 74.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 37.3 GB (IQ2_XS) to 132.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
mistralai.Mistral Medium 3.5 128B is a 125B-parameter Mistral model in GGUF format, quantized by DevQuasar. Its trained context length is 256K tokens. The repository has 7 quant files, from 37.3 GB (IQ2_XS) to 132.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 37.3 GB | 40.8 GB | Too big | Get file → | |
| Q2_K | 46.6 GB (3 parts) | 50.0 GB | Too big | Get file → | |
| Q3_K_M | 60.6 GB (4 parts) | 64.1 GB | Too big | Get file → | |
| Q4_K_M | 74.9 GB (5 parts) | 78.3 GB | Too big | Get file → | |
| Q5_K_M | 88.3 GB (6 parts) | 91.8 GB | Too big | Get file → | |
| Q6_K | 102.6 GB (7 parts) | 106.0 GB | Too big | Get file → | |
| Q8_0 | 132.9 GB (9 parts) | 136.3 GB | Too big | Get file → |
What GPU do you need for mistralai.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: 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: the best quant that fits is IQ2_XS (37.3 GB file, about 40.8 GB in use).
Which mistralai.Mistral Medium 3.5 128B quant should you choose?
Q4_K_M is the usual starting point for mistralai.Mistral Medium 3.5 128B: it balances file size and quality well. Here it is a 74.9 GB file.
The Q8_0 file is 132.9 GB, about 1.8 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 IQ2_XS at 37.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mistralai.Mistral Medium 3.5 128B
How much VRAM does mistralai.Mistral Medium 3.5 128B need?
About 78.3 GB at Q4_K_M with an 8K context window. That is the 74.9 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 mistralai.Mistral Medium 3.5 128B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 40.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of mistralai.Mistral Medium 3.5 128B GGUF?
It depends on the quant: IQ2_XS is 37.3 GB, Q2_K is 46.6 GB, Q3_K_M is 60.6 GB, Q4_K_M is 74.9 GB, Q5_K_M is 88.3 GB, Q6_K is 102.6 GB and 1 more.
What context length does mistralai.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 mistralai.Mistral Medium 3.5 128B GGUF?
The files are on Hugging Face in the DevQuasar/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 mistralai.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.