Hugging Face's logo

second-state
/
Codestral-22B-v0.1-GGUF

Text Generation
Transformers
GGUF
code
mistral
Model card Files Community
apepkuss79 commited on
Commit
4ef4566
·
verified ·
1 Parent(s): 514d351

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -67,17 +67,17 @@ language:
67
  | Name | Quant method | Bits | Size | Use case |
68
  | ---- | ---- | ---- | ---- | ----- |
69
  | [Codestral-22B-v0.1-hf-Q2_K.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q2_K.gguf) | Q2_K | 2 | 8.27 GB| smallest, significant quality loss - not recommended for most purposes |
70
- | [Codestral-22B-v0.1-hf-Q3_K_L.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q3_K_L.gguf) | Q3_K_L | 3 | 11.7 GB| small, substantial quality loss |
71
- | [Codestral-22B-v0.1-hf-Q3_K_M.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q3_K_M.gguf) | Q3_K_M | 3 | 10.8 GB| very small, high quality loss |
72
- | [Codestral-22B-v0.1-hf-Q3_K_S.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q3_K_S.gguf) | Q3_K_S | 3 | 9.64 GB| very small, high quality loss |
73
- | [Codestral-22B-v0.1-hf-Q4_0.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q4_0.gguf) | Q4_0 | 4 | 12.6 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
74
- | [Codestral-22B-v0.1-hf-Q4_K_M.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q4_K_M.gguf) | Q4_K_M | 4 | 13.3 GB| medium, balanced quality - recommended |
75
- | [Codestral-22B-v0.1-hf-Q4_K_S.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q4_K_S.gguf) | Q4_K_S | 4 | 12.7 GB| small, greater quality loss |
76
- | [Codestral-22B-v0.1-hf-Q5_0.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q5_0.gguf) | Q5_0 | 5 | 15.3 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
77
- | [Codestral-22B-v0.1-hf-Q5_K_M.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q5_K_M.gguf) | Q5_K_M | 5 | 15.7 GB| large, very low quality loss - recommended |
78
- | [Codestral-22B-v0.1-hf-Q5_K_S.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q5_K_S.gguf) | Q5_K_S | 5 | 15.3 GB| large, low quality loss - recommended |
79
- | [Codestral-22B-v0.1-hf-Q6_K.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q6_K.gguf) | Q6_K | 6 | 18.3 GB| very large, extremely low quality loss |
80
- | [Codestral-22B-v0.1-hf-Q8_0.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-Q8_0.gguf) | Q8_0 | 8 | 23.6 GB| very large, extremely low quality loss - not recommended |
81
- | [Codestral-22B-v0.1-hf-f16.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-hf-GGUF/blob/main/Codestral-22B-v0.1-hf-f16.gguf) | f16 | 16 | 44.5 GB| |
82
 
83
  *Quantized with llama.cpp b3030.*
 
67
  | Name | Quant method | Bits | Size | Use case |
68
  | ---- | ---- | ---- | ---- | ----- |
69
  | [Codestral-22B-v0.1-hf-Q2_K.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q2_K.gguf) | Q2_K | 2 | 8.27 GB| smallest, significant quality loss - not recommended for most purposes |
70
+ | [Codestral-22B-v0.1-hf-Q3_K_L.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q3_K_L.gguf) | Q3_K_L | 3 | 11.7 GB| small, substantial quality loss |
71
+ | [Codestral-22B-v0.1-hf-Q3_K_M.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q3_K_M.gguf) | Q3_K_M | 3 | 10.8 GB| very small, high quality loss |
72
+ | [Codestral-22B-v0.1-hf-Q3_K_S.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q3_K_S.gguf) | Q3_K_S | 3 | 9.64 GB| very small, high quality loss |
73
+ | [Codestral-22B-v0.1-hf-Q4_0.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q4_0.gguf) | Q4_0 | 4 | 12.6 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
74
+ | [Codestral-22B-v0.1-hf-Q4_K_M.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q4_K_M.gguf) | Q4_K_M | 4 | 13.3 GB| medium, balanced quality - recommended |
75
+ | [Codestral-22B-v0.1-hf-Q4_K_S.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q4_K_S.gguf) | Q4_K_S | 4 | 12.7 GB| small, greater quality loss |
76
+ | [Codestral-22B-v0.1-hf-Q5_0.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q5_0.gguf) | Q5_0 | 5 | 15.3 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
77
+ | [Codestral-22B-v0.1-hf-Q5_K_M.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q5_K_M.gguf) | Q5_K_M | 5 | 15.7 GB| large, very low quality loss - recommended |
78
+ | [Codestral-22B-v0.1-hf-Q5_K_S.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q5_K_S.gguf) | Q5_K_S | 5 | 15.3 GB| large, low quality loss - recommended |
79
+ | [Codestral-22B-v0.1-hf-Q6_K.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q6_K.gguf) | Q6_K | 6 | 18.3 GB| very large, extremely low quality loss |
80
+ | [Codestral-22B-v0.1-hf-Q8_0.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-Q8_0.gguf) | Q8_0 | 8 | 23.6 GB| very large, extremely low quality loss - not recommended |
81
+ | [Codestral-22B-v0.1-hf-f16.gguf](https://huggingface.co/second-state/Codestral-22B-v0.1-GGUF/blob/main/Codestral-22B-v0.1-hf-f16.gguf) | f16 | 16 | 44.5 GB| |
82
 
83
  *Quantized with llama.cpp b3030.*