Mistral Crab SFT needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 2.5 GB (IQ2_M) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Mistral Crab SFT is a 7.25B-parameter Mistral model in GGUF format, quantized by bartowski. Its trained context length is 32K tokens. The repository has 24 quant files, from 2.5 GB (IQ2_M) to 14.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q2_K_L | 2.9 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_S | 3.2 GB | 4.7 GB | Fits | Get file → | |
| IQ3_M | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 5.4 GB | Fits | Get file → | |
| IQ4_XS | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_XL | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_S | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_L | 4.5 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_L | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q6_K | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q6_K_L | 6.0 GB | 7.6 GB | Tight | Get file → | |
| Q8_0 | 7.7 GB | 9.3 GB | Too big | Get file → | |
| F16 | 14.5 GB | 16.1 GB | Too big | Get file → |
What GPU do you need for Mistral Crab SFT?
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 Q4_K_L (4.5 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K_L (6.0 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).
Which Mistral Crab SFT quant should you choose?
Q4_K_M is the usual starting point for Mistral Crab SFT: it balances file size and quality well. Here it is a 4.4 GB file.
The Q8_0 file is 7.7 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_M at 2.5 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
Source
Frequently asked questions about Mistral Crab SFT
How much VRAM does Mistral Crab SFT need?
About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Crab SFT on an 8 GB GPU?
Yes, with Q6_K_L: the 6.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral Crab SFT GGUF?
It depends on the quant: IQ2_M is 2.5 GB, Q2_K is 2.7 GB, Q2_K_L is 2.9 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_M is 3.3 GB and 18 more.
What context length does Mistral Crab SFT support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Mistral Crab SFT GGUF?
The files are on Hugging Face in the bartowski/Mistral-Crab-SFT-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 Crab SFT 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.