Hugging Face's logo

mradermacher
/
GigaChat-20B-A3B-instruct-GGUF

Transformers
GGUF
Russian
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
7e2573a
·
verified ·
1 Parent(s): 0e5e077

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -34,9 +34,11 @@ more details, including on how to concatenate multi-part files.
34
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q3_K_S.gguf) | Q3_K_S | 9.1 | |
35
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q3_K_M.gguf) | Q3_K_M | 10.0 | lower quality |
36
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q3_K_L.gguf) | Q3_K_L | 10.8 | |
 
37
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q4_K_S.gguf) | Q4_K_S | 11.8 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q4_K_M.gguf) | Q4_K_M | 12.6 | fast, recommended |
39
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q5_K_S.gguf) | Q5_K_S | 14.3 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q6_K.gguf) | Q6_K | 17.0 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q8_0.gguf) | Q8_0 | 22.0 | fast, best quality |
42
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q3_K_S.gguf) | Q3_K_S | 9.1 | |
35
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q3_K_M.gguf) | Q3_K_M | 10.0 | lower quality |
36
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q3_K_L.gguf) | Q3_K_L | 10.8 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.IQ4_XS.gguf) | IQ4_XS | 11.2 | |
38
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q4_K_S.gguf) | Q4_K_S | 11.8 | fast, recommended |
39
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q4_K_M.gguf) | Q4_K_M | 12.6 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q5_K_S.gguf) | Q5_K_S | 14.3 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q5_K_M.gguf) | Q5_K_M | 14.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q6_K.gguf) | Q6_K | 17.0 | very good quality |
43
  | [GGUF](https://huggingface.co/mradermacher/GigaChat-20B-A3B-instruct-GGUF/resolve/main/GigaChat-20B-A3B-instruct.Q8_0.gguf) | Q8_0 | 22.0 | fast, best quality |
44