mradermacher commited on
Commit
e59e5b3
·
verified ·
1 Parent(s): 9c443ad

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -41,11 +41,13 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q3_K_S.gguf) | Q3_K_S | 14.5 | |
42
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q3_K_M.gguf) | Q3_K_M | 16.1 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q4_K_S.gguf) | Q4_K_S | 19.0 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q4_K_M.gguf) | Q4_K_M | 20.3 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q5_K_S.gguf) | Q5_K_S | 22.9 | |
47
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q5_K_M.gguf) | Q5_K_M | 23.7 | |
48
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q6_K.gguf) | Q6_K | 27.4 | very good quality |
 
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
 
41
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q3_K_S.gguf) | Q3_K_S | 14.5 | |
42
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q3_K_M.gguf) | Q3_K_M | 16.1 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.IQ4_XS.gguf) | IQ4_XS | 18.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q4_K_S.gguf) | Q4_K_S | 19.0 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q4_K_M.gguf) | Q4_K_M | 20.3 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q5_K_S.gguf) | Q5_K_S | 22.9 | |
48
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q5_K_M.gguf) | Q5_K_M | 23.7 | |
49
  | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q6_K.gguf) | Q6_K | 27.4 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/GroveMoE-Inst-GGUF/resolve/main/GroveMoE-Inst.Q8_0.gguf) | Q8_0 | 35.2 | fast, best quality |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):