Hugging Face's logo

mradermacher
/
koishi-8x7b-qlora-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
9afe600
•
1 Parent(s): b19c290

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -29,8 +29,19 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ3_S.gguf) | IQ3_S | 20.5 | beats Q3_K* |
 
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
 
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |
35
 
36
 
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q2_K.gguf) | Q2_K | 17.4 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ3_XS.gguf) | IQ3_XS | 19.5 | |
34
  | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ3_S.gguf) | IQ3_S | 20.5 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ3_M.gguf) | IQ3_M | 21.5 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q3_K_M.gguf) | Q3_K_M | 22.6 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q3_K_L.gguf) | Q3_K_L | 24.3 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.IQ4_XS.gguf) | IQ4_XS | 25.5 | |
40
  | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q5_K_S.gguf) | Q5_K_S | 32.3 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q5_K_M.gguf) | Q5_K_M | 33.3 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/koishi-8x7b-qlora-GGUF/resolve/main/koishi-8x7b-qlora.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |
46
 
47