Mistral Large 3 675B Base 2512 i1 needs about 167.8 GB of memory at IQ1_M (a 149.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 0.6 GB to 197.6 GB (IQ2_S).
Mistral Large 3 675B Base 2512 i1 is a 673B-parameter Mistral model in GGUF format, quantized by mradermacher. Its trained context length is 288K tokens. The repository has 6 quant files, from 0.6 GB to 197.6 GB (IQ2_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 134.0 GB | 150.6 GB | Too big | Get file → | |
| IQ1_M | 149.4 GB | 167.8 GB | Too big | Get file → | |
| IQ2_XXS | 175.0 GB | 196.5 GB | Too big | Get file → | |
| IQ2_XS | 195.7 GB | 219.7 GB | Too big | Get file → | |
| IQ2_S | 197.6 GB | 221.9 GB | Too big | Get file → |
What GPU do you need for Mistral Large 3 675B Base 2512 i1?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.6 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 1.2 GB in use).
Which Mistral Large 3 675B Base 2512 i1 quant should you choose?
IQ1_M (149.4 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is the first one in the table at 0.6 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 Large 3 675B Base 2512 i1
How much VRAM does Mistral Large 3 675B Base 2512 i1 need?
About 167.8 GB at IQ1_M with an 8K context window. That is the 149.4 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 Large 3 675B Base 2512 i1 on an 8 GB GPU?
Yes, with the smaller files: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral Large 3 675B Base 2512 i1 GGUF?
It depends on the quant: file is 0.6 GB, IQ1_S is 134.0 GB, IQ1_M is 149.4 GB, IQ2_XXS is 175.0 GB, IQ2_XS is 195.7 GB, IQ2_S is 197.6 GB.
What context length does Mistral Large 3 675B Base 2512 i1 support?
The GGUF header lists a trained context length of 294,912 tokens (288K).
Where can I download Mistral Large 3 675B Base 2512 i1 GGUF?
The files are on Hugging Face in the mradermacher/Mistral-Large-3-675B-Base-2512-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 Large 3 675B Base 2512 i1 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.