Hugging Face's logo

mradermacher
/
RoGemma-7b-Instruct-2024-10-09-GGUF

Transformers
GGUF
Romanian
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
0286188
·
verified ·
1 Parent(s): 61095b9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -43,10 +43,14 @@ more details, including on how to concatenate multi-part files.
43
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q3_K_S.gguf) | Q3_K_S | 4.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q6_K.gguf) | Q6_K | 7.1 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality |
 
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
43
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q3_K_S.gguf) | Q3_K_S | 4.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.IQ4_XS.gguf) | IQ4_XS | 4.9 | |
47
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q5_K_S.gguf) | Q5_K_S | 6.1 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q5_K_M.gguf) | Q5_K_M | 6.2 | |
51
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q6_K.gguf) | Q6_K | 7.1 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/RoGemma-7b-Instruct-2024-10-09-GGUF/resolve/main/RoGemma-7b-Instruct-2024-10-09.f16.gguf) | f16 | 17.2 | 16 bpw, overkill |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):