Hugging Face's logo

TheBloke
/
Mixtral-8x7B-v0.1-GGUF

Transformers
GGUF
5 languages
mixtral
text-generation-inference
Model card Files Community
21
TheBloke commited on
Commit
c756bba
•
1 Parent(s): 6348bb4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -7
README.md CHANGED
@@ -95,15 +95,9 @@ Refer to the Provided Files table below to see what files use which methods, and
95
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
96
  | ---- | ---- | ---- | ---- | ---- | ----- |
97
  | [mixtral-8x7b-v0.1.Q2_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
98
- | [mixtral-8x7b-v0.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q3_K_S.gguf) | Q3_K_S | 3 | 20.29 GB| 22.79 GB | very small, high quality loss |
99
- | [mixtral-8x7b-v0.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss |
100
- | [mixtral-8x7b-v0.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q3_K_L.gguf) | Q3_K_L | 3 | 20.43 GB| 22.93 GB | small, substantial quality loss |
101
  | [mixtral-8x7b-v0.1.Q4_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
102
- | [mixtral-8x7b-v0.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_M.gguf) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended |
103
- | [mixtral-8x7b-v0.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_S.gguf) | Q4_K_S | 4 | 26.44 GB| 28.94 GB | small, greater quality loss |
104
  | [mixtral-8x7b-v0.1.Q5_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
105
- | [mixtral-8x7b-v0.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q5_K_M.gguf) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended |
106
- | [mixtral-8x7b-v0.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q5_K_S.gguf) | Q5_K_S | 5 | 32.23 GB| 34.73 GB | large, low quality loss - recommended |
107
  | [mixtral-8x7b-v0.1.Q6_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss |
108
  | [mixtral-8x7b-v0.1.Q8_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended |
109
 
 
95
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
96
  | ---- | ---- | ---- | ---- | ---- | ----- |
97
  | [mixtral-8x7b-v0.1.Q2_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
98
+ | [mixtral-8x7b-v0.1.Q3_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss |
 
 
99
  | [mixtral-8x7b-v0.1.Q4_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
 
 
100
  | [mixtral-8x7b-v0.1.Q5_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
 
 
101
  | [mixtral-8x7b-v0.1.Q6_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss |
102
  | [mixtral-8x7b-v0.1.Q8_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended |
103