mradermacher commited on
Commit
03480d1
·
verified ·
1 Parent(s): 33febcd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -33,10 +33,14 @@ more details, including on how to concatenate multi-part files.
33
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
34
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
35
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
 
36
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
37
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
39
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
33
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
34
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
35
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
37
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
41
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
42
  | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/FsfairX-Zephyr-Chat-v0.1-GGUF/resolve/main/FsfairX-Zephyr-Chat-v0.1.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant
46
  types (lower is better):