Mistral-Medium-3.5-128B needs about 85.8 GB of memory at Q4_K_M (a 82.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 60.0 GB (IQ3_S) to 97.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
Mistral-Medium-3.5-128B is a 125B-parameter Mistral model in GGUF format, quantized by vultr. Its trained context length is 256K tokens. The repository has 4 quant files, from 60.0 GB (IQ3_S) to 97.1 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 60.0 GB | 63.4 GB | Too big | Get file → | |
| IQ3_M | 62.5 GB | 65.9 GB | Too big | Get file → | |
| Q4_K_M | 82.4 GB | 85.8 GB | Too big | Get file → | |
| Q5_K_M | 97.1 GB | 100.6 GB | Too big | Get file → |
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: 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-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 82.4 GB file.
If memory is tight, the smallest file is IQ3_S at 60.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 85.8 GB at Q4_K_M with an 8K context window. That is the 82.4 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?
Not at an 8K context. The smallest file needs about 63.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral-Medium-3.5-128B GGUF?
It depends on the quant: IQ3_S is 60.0 GB, IQ3_M is 62.5 GB, Q4_K_M is 82.4 GB, Q5_K_M is 97.1 GB.
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 vultr/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.