Hugging Face's logo

mradermacher
/
command-4-v01-Finetuned-merged-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
64693dd
·
verified ·
1 Parent(s): 9fb7a0b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -30,7 +30,16 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q2_K.gguf) | Q2_K | 13.9 | |
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q4_K_S.gguf) | Q4_K_S | 20.5 | fast, recommended |
 
 
 
 
 
34
 
35
  Here is a handy graph by ikawrakow comparing some lower-quality quant
36
  types (lower is better):
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q2_K.gguf) | Q2_K | 13.9 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q3_K_S.gguf) | Q3_K_S | 16.0 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q3_K_M.gguf) | Q3_K_M | 17.7 | lower quality |
35
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q3_K_L.gguf) | Q3_K_L | 19.2 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.IQ4_XS.gguf) | IQ4_XS | 19.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q4_K_S.gguf) | Q4_K_S | 20.5 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q4_K_M.gguf) | Q4_K_M | 21.6 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q5_K_S.gguf) | Q5_K_S | 24.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q5_K_M.gguf) | Q5_K_M | 25.1 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q6_K.gguf) | Q6_K | 28.8 | very good quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/command-4-v01-Finetuned-merged-GGUF/resolve/main/command-4-v01-Finetuned-merged.Q8_0.gguf) | Q8_0 | 37.3 | fast, best quality |
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):