Hugging Face's logo

bartowski
/
Codestral-22B-v0.1-GGUF

Text Generation
GGUF
code
Model card Files Community
3
bartowski commited on
Commit
db6b51b
•
1 Parent(s): e52eda6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -5
README.md CHANGED
@@ -41,12 +41,10 @@ No chat template specified so default is used. This may be incorrect, check orig
41
  | [Codestral-22B-v0.1-Q5_K_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q5_K_S.gguf) | Q5_K_S | 15.32GB | High quality, *recommended*. |
42
  | [Codestral-22B-v0.1-Q4_K_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q4_K_M.gguf) | Q4_K_M | 13.34GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
43
  | [Codestral-22B-v0.1-Q4_K_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q4_K_S.gguf) | Q4_K_S | 12.66GB | Slightly lower quality with more space savings, *recommended*. |
44
- | [Codestral-22B-v0.1-IQ4_NL.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF//main/Codestral-22B-v0.1-IQ4_NL.gguf) | IQ4_NL | | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
45
  | [Codestral-22B-v0.1-IQ4_XS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ4_XS.gguf) | IQ4_XS | 11.93GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
46
  | [Codestral-22B-v0.1-Q3_K_L.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q3_K_L.gguf) | Q3_K_L | 11.73GB | Lower quality but usable, good for low RAM availability. |
47
  | [Codestral-22B-v0.1-Q3_K_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q3_K_M.gguf) | Q3_K_M | 10.75GB | Even lower quality. |
48
  | [Codestral-22B-v0.1-IQ3_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ3_M.gguf) | IQ3_M | 10.06GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
49
- | [Codestral-22B-v0.1-IQ3_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF//main/Codestral-22B-v0.1-IQ3_S.gguf) | IQ3_S | | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
50
  | [Codestral-22B-v0.1-Q3_K_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q3_K_S.gguf) | Q3_K_S | 9.64GB | Low quality, not recommended. |
51
  | [Codestral-22B-v0.1-IQ3_XS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ3_XS.gguf) | IQ3_XS | 9.17GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
52
  | [Codestral-22B-v0.1-IQ3_XXS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ3_XXS.gguf) | IQ3_XXS | 8.59GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
@@ -54,9 +52,6 @@ No chat template specified so default is used. This may be incorrect, check orig
54
  | [Codestral-22B-v0.1-IQ2_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ2_M.gguf) | IQ2_M | 7.61GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
55
  | [Codestral-22B-v0.1-IQ2_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ2_S.gguf) | IQ2_S | 7.03GB | Very low quality, uses SOTA techniques to be usable. |
56
  | [Codestral-22B-v0.1-IQ2_XS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ2_XS.gguf) | IQ2_XS | 6.64GB | Very low quality, uses SOTA techniques to be usable. |
57
- | [Codestral-22B-v0.1-IQ2_XXS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF//main/Codestral-22B-v0.1-IQ2_XXS.gguf) | IQ2_XXS | | Lower quality, uses SOTA techniques to be usable. |
58
- | [Codestral-22B-v0.1-IQ1_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF//main/Codestral-22B-v0.1-IQ1_M.gguf) | IQ1_M | | Extremely low quality, *not* recommended. |
59
- | [Codestral-22B-v0.1-IQ1_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF//main/Codestral-22B-v0.1-IQ1_S.gguf) | IQ1_S | | Extremely low quality, *not* recommended. |
60
 
61
  ## Downloading using huggingface-cli
62
 
 
41
  | [Codestral-22B-v0.1-Q5_K_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q5_K_S.gguf) | Q5_K_S | 15.32GB | High quality, *recommended*. |
42
  | [Codestral-22B-v0.1-Q4_K_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q4_K_M.gguf) | Q4_K_M | 13.34GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
43
  | [Codestral-22B-v0.1-Q4_K_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q4_K_S.gguf) | Q4_K_S | 12.66GB | Slightly lower quality with more space savings, *recommended*. |
 
44
  | [Codestral-22B-v0.1-IQ4_XS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ4_XS.gguf) | IQ4_XS | 11.93GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
45
  | [Codestral-22B-v0.1-Q3_K_L.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q3_K_L.gguf) | Q3_K_L | 11.73GB | Lower quality but usable, good for low RAM availability. |
46
  | [Codestral-22B-v0.1-Q3_K_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q3_K_M.gguf) | Q3_K_M | 10.75GB | Even lower quality. |
47
  | [Codestral-22B-v0.1-IQ3_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ3_M.gguf) | IQ3_M | 10.06GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
 
48
  | [Codestral-22B-v0.1-Q3_K_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-Q3_K_S.gguf) | Q3_K_S | 9.64GB | Low quality, not recommended. |
49
  | [Codestral-22B-v0.1-IQ3_XS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ3_XS.gguf) | IQ3_XS | 9.17GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
50
  | [Codestral-22B-v0.1-IQ3_XXS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ3_XXS.gguf) | IQ3_XXS | 8.59GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
 
52
  | [Codestral-22B-v0.1-IQ2_M.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ2_M.gguf) | IQ2_M | 7.61GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
53
  | [Codestral-22B-v0.1-IQ2_S.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ2_S.gguf) | IQ2_S | 7.03GB | Very low quality, uses SOTA techniques to be usable. |
54
  | [Codestral-22B-v0.1-IQ2_XS.gguf](https://huggingface.co/bartowski/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-IQ2_XS.gguf) | IQ2_XS | 6.64GB | Very low quality, uses SOTA techniques to be usable. |
 
 
 
55
 
56
  ## Downloading using huggingface-cli
57