bullerwins Codestral 22B v0.1 hf needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.0 GB (Q4_K_M) to 18.3 GB (Q6_K).
bullerwins Codestral 22B v0.1 hf is a 22B-parameter Mistral model in GGUF format, quantized by RichardErkhov. The repository has 21 quant files, from 0.0 GB (Q4_K_M) to 18.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ4_NL | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q3_K | 0.9 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q5_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| IQ4_XS | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q3_K_L | 6.0 GB | 7.2 GB | Tight | Get file → | |
| Q2_K | 8.3 GB | 9.8 GB | Too big | Get file → | |
| IQ3_XS | 9.2 GB | 10.8 GB | Too big | Get file → | |
| Q3_K_S | 9.6 GB | 11.3 GB | Too big | Get file → | |
| IQ3_S | 9.7 GB | 11.4 GB | Too big | Get file → | |
| Q3_K_M | 10.8 GB | 12.5 GB | Too big | Get file → | |
| Q5_K_S | 15.3 GB | 17.7 GB | Too big | Get file → | |
| Q5_K | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_1 | 16.7 GB | 19.2 GB | Too big | Get file → | |
| Q6_K | 18.3 GB | 20.9 GB | Too big | Get file → |
What GPU do you need for bullerwins Codestral 22B v0.1 hf?
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 Q5_0 (2.7 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (3.5 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_L (6.0 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_S (9.7 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (10.8 GB file, about 12.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.9 GB in use).
Which bullerwins Codestral 22B v0.1 hf quant should you choose?
Q4_K_M is the usual starting point for bullerwins Codestral 22B v0.1 hf: it balances file size and quality well. Here it is a 0.0 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about bullerwins Codestral 22B v0.1 hf
How much VRAM does bullerwins Codestral 22B v0.1 hf need?
About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 bullerwins Codestral 22B v0.1 hf on an 8 GB GPU?
Yes, with Q3_K_L: the 6.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bullerwins Codestral 22B v0.1 hf GGUF?
It depends on the quant: Q4_K_M is 0.0 GB, Q4_K is 0.1 GB, Q4_K_S is 0.2 GB, IQ4_NL is 0.6 GB, Q3_K is 0.9 GB, IQ3_M is 1.6 GB and 15 more.
Where can I download bullerwins Codestral 22B v0.1 hf GGUF?
The files are on Hugging Face in the RichardErkhov/bullerwins_-_Codestral-22B-v0.1-hf-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.