Hugging Face's logo

mradermacher
/
Rocinante-Prism_V1.0-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
cc67d71
·
verified ·
1 Parent(s): cc0de01

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -32,7 +32,18 @@ more details, including on how to concatenate multi-part files.
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q2_K.gguf) | Q2_K | 4.1 | |
 
 
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q4_K_S.gguf) | Q4_K_S | 6.0 | fast, recommended |
 
 
 
 
 
 
36
 
37
  Here is a handy graph by ikawrakow comparing some lower-quality quant
38
  types (lower is better):
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q2_K.gguf) | Q2_K | 4.1 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q3_K_L.gguf) | Q3_K_L | 5.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.IQ4_XS.gguf) | IQ4_XS | 5.7 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.9 | fast on arm, low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q4_K_S.gguf) | Q4_K_S | 6.0 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q5_K_S.gguf) | Q5_K_S | 7.1 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q5_K_M.gguf) | Q5_K_M | 7.3 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q6_K.gguf) | Q6_K | 8.4 | very good quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.Q8_0.gguf) | Q8_0 | 10.8 | fast, best quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Rocinante-Prism_V1.0-GGUF/resolve/main/Rocinante-Prism_V1.0.f16.gguf) | f16 | 20.2 | 16 bpw, overkill |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):