mradermacher commited on
Commit
20b7018
·
verified ·
1 Parent(s): 1b92771

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -33,6 +33,15 @@ more details, including on how to concatenate multi-part files.
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q2_K.gguf) | Q2_K | 12.9 | |
 
 
 
 
 
 
 
 
 
36
 
37
  Here is a handy graph by ikawrakow comparing some lower-quality quant
38
  types (lower is better):
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q2_K.gguf) | Q2_K | 12.9 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q3_K_S.gguf) | Q3_K_S | 15.1 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q3_K_M.gguf) | Q3_K_M | 16.8 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q3_K_L.gguf) | Q3_K_L | 18.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q4_K_S.gguf) | Q4_K_S | 19.7 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q4_K_M.gguf) | Q4_K_M | 20.8 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q5_K_S.gguf) | Q5_K_S | 23.8 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q5_K_M.gguf) | Q5_K_M | 24.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q6_K.gguf) | Q6_K | 28.3 | very good quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-pruned50-GGUF/resolve/main/Nous-Hermes-2-Yi-34B-pruned50.Q8_0.gguf) | Q8_0 | 36.6 | fast, best quality |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):