Mistral Evolved 11b v0.1 needs about 9.3 GB of memory at Q4_K (a 7.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 16 quants, from 3.5 GB (IQ2_XXS) to 44.7 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.
Mistral Evolved 11b v0.1 is a 11.2B-parameter Mistral model in GGUF format, quantized by itsdotscience. Its trained context length is 32K tokens. The repository has 16 quant files, from 3.5 GB (IQ2_XXS) to 44.7 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 3.5 GB | 5.6 GB | Fits | Get file → | |
| Q2_K | 4.6 GB | 6.8 GB | Fits | Get file → | |
| Q3_K_S | 5.3 GB | 7.4 GB | Tight | Get file → | |
| Q3_K | 5.8 GB | 8.0 GB | Tight | Get file → | |
| Q3_K_L | 6.3 GB | 8.5 GB | Too big | Get file → | |
| Q4_0 | 6.8 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_S | 6.8 GB | 9.0 GB | Too big | Get file → | |
| Q4_K | 7.1 GB | 9.3 GB | Too big | Get file → | |
| Q4_1 | 7.4 GB | 9.6 GB | Too big | Get file → | |
| Q5_K_S | 8.1 GB | 10.3 GB | Too big | Get file → | |
| Q5_0 | 8.1 GB | 10.3 GB | Too big | Get file → | |
| Q5_1 | 8.8 GB | 11.0 GB | Too big | Get file → | |
| Q6_K | 9.6 GB | 11.8 GB | Too big | Get file → | |
| Q8_0 | 12.3 GB | 14.4 GB | Too big | Get file → | |
| F16 | 22.6 GB | 24.8 GB | Too big | Get file → | |
| F32 | 44.7 GB | 46.8 GB | Too big | Get file → |
What GPU do you need for Mistral Evolved 11b v0.1?
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: the best quant that fits is IQ2_XXS (3.5 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K (5.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.3 GB file, about 14.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.3 GB file, about 14.4 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (22.6 GB file, about 24.8 GB in use).
- 48 GB VRAM: the best quant that fits is F32 (44.7 GB file, about 46.8 GB in use).
Which Mistral Evolved 11b v0.1 quant should you choose?
Q4_K (7.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_XXS at 3.5 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
Frequently asked questions about Mistral Evolved 11b v0.1
How much VRAM does Mistral Evolved 11b v0.1 need?
About 9.3 GB at Q4_K with an 8K context window. That is the 7.1 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 Evolved 11b v0.1 on an 8 GB GPU?
Yes, with Q3_K: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral Evolved 11b v0.1 GGUF?
It depends on the quant: IQ2_XXS is 3.5 GB, Q2_K is 4.6 GB, Q3_K_S is 5.3 GB, Q3_K is 5.8 GB, Q3_K_L is 6.3 GB, Q4_0 is 6.8 GB and 10 more.
What context length does Mistral Evolved 11b v0.1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.
Where can I download Mistral Evolved 11b v0.1 GGUF?
The files are on Hugging Face in the itsdotscience/Mistral-Evolved-11b-v0.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.