Mistral 24B needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 13.4 GB (Q4_0) to 16.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Mistral 24B is a 23.6B-parameter Mistral model in GGUF format, quantized by AlSamCur123. Its trained context length is 32K tokens. The repository has 6 quant files, from 13.4 GB (Q4_0) to 16.8 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 13.4 GB | 15.3 GB | Too big | Get file → | |
| Q4_0 | 13.4 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → |
What GPU do you need for Mistral 24B?
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: the best quant that fits is Q4_0 (13.4 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (16.8 GB file, about 18.6 GB in use).
Which Mistral 24B quant should you choose?
Q4_K_M is the usual starting point for Mistral 24B: it balances file size and quality well. Here it is a 14.3 GB file.
If memory is tight, the smallest file is Q4_0 at 13.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mistral 24B
How much VRAM does Mistral 24B need?
About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 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 24B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral 24B GGUF?
It depends on the quant: Q4_0 is 13.4 GB, Q4_0 is 13.4 GB, Q4_K_M is 14.3 GB, Q4_K_M is 14.3 GB, Q5_K_M is 16.8 GB, Q5_K_M is 16.8 GB.
What context length does Mistral 24B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Mistral 24B GGUF?
The files are on Hugging Face in the AlSamCur123/Mistral-24B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.