Hugging Face's logo

mradermacher
/
LLaMAX2-7B-X-CSQA-GGUF

Transformers
GGUF
Multilingual
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
a501005
·
verified ·
1 Parent(s): c5c7d42

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -135,9 +135,13 @@ more details, including on how to concatenate multi-part files.
135
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
136
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
137
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
138
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
139
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
 
 
140
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
 
141
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
142
 
143
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
135
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
136
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
137
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
138
+ | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
139
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
140
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
141
+ | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
142
+ | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
143
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
144
+ | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
145
  | [GGUF](https://huggingface.co/mradermacher/LLaMAX2-7B-X-CSQA-GGUF/resolve/main/LLaMAX2-7B-X-CSQA.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
146
 
147
  Here is a handy graph by ikawrakow comparing some lower-quality quant