mradermacher commited on
Commit
043429b
·
verified ·
1 Parent(s): eadecb5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -46,9 +46,15 @@ more details, including on how to concatenate multi-part files.
46
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q2_K.gguf) | Q2_K | 2.7 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
 
 
49
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
 
 
 
50
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q8_0.gguf) | Q8_0 | 7.2 | fast, best quality |
 
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
 
46
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q2_K.gguf) | Q2_K | 2.7 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.IQ4_XS.gguf) | IQ4_XS | 3.8 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q5_K_S.gguf) | Q5_K_S | 4.7 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.Q8_0.gguf) | Q8_0 | 7.2 | fast, best quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/Lucie-7B-Instruct-v1.1-GGUF/resolve/main/Lucie-7B-Instruct-v1.1.f16.gguf) | f16 | 13.5 | 16 bpw, overkill |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant
60
  types (lower is better):