mradermacher
commited on
Commit
•
3c643b4
1
Parent(s):
9be9b1d
auto-patch README.md
Browse files
README.md
CHANGED
@@ -41,6 +41,7 @@ more details, including on how to concatenate multi-part files.
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
|
|
44 |
|
45 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
46 |
types (lower is better):
|
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-7b-uncensored-GGUF/resolve/main/qwen2.5-7b-uncensored.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
|
45 |
|
46 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
47 |
types (lower is better):
|