Hugging Face's logo

mradermacher
/
Mixtral_7Bx5_MoE_30B-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b1df205
·
verified ·
1 Parent(s): b47d506

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -29,8 +29,17 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.IQ3_S.gguf) | IQ3_S | 13.0 | beats Q3_K* |
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q4_K_S.gguf) | Q4_K_S | 17.0 | fast, recommended |
 
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q8_0.gguf) | Q8_0 | 31.8 | fast, best quality |
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q2_K.gguf) | Q2_K | 11.0 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q3_K_S.gguf) | Q3_K_S | 13.0 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.IQ3_S.gguf) | IQ3_S | 13.0 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.IQ3_M.gguf) | IQ3_M | 13.2 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q3_K_M.gguf) | Q3_K_M | 14.4 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q3_K_L.gguf) | Q3_K_L | 15.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q4_K_S.gguf) | Q4_K_S | 17.0 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q4_K_M.gguf) | Q4_K_M | 18.1 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q5_K_S.gguf) | Q5_K_S | 20.6 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q5_K_M.gguf) | Q5_K_M | 21.2 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q6_K.gguf) | Q6_K | 24.5 | very good quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Mixtral_7Bx5_MoE_30B-GGUF/resolve/main/Mixtral_7Bx5_MoE_30B.Q8_0.gguf) | Q8_0 | 31.8 | fast, best quality |
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant