Hugging Face's logo

mradermacher
/
Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF

Transformers
GGUF
Japanese
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
6ccea75
·
verified ·
1 Parent(s): 9bf4545

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -30,7 +30,10 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q2_K.gguf) | Q2_K | 17.4 | |
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
 
34
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q2_K.gguf) | Q2_K | 17.4 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q3_K_M.gguf) | Q3_K_M | 22.6 | lower quality |
35
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
36
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
37
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-GGUF/resolve/main/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant