Hugging Face's logo

mradermacher
/
Quasar-2.0-7B-Pro-GGUF

Transformers
GGUF
English
Generated from Trainer
open-r1
trl
sft
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
c4b5576
·
verified ·
1 Parent(s): 5e6fa57

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -42,8 +42,11 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
42
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Quasar-2.0-7B-Pro-GGUF/resolve/main/Quasar-2.0-7B-Pro.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):