mradermacher commited on
Commit
9402769
·
verified ·
1 Parent(s): 4f1516d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -52,12 +52,15 @@ more details, including on how to concatenate multi-part files.
52
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q2_K.gguf) | Q2_K | 3.4 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q3_K_S.gguf) | Q3_K_S | 3.9 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality |
 
55
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.IQ4_XS.gguf) | IQ4_XS | 4.7 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended |
57
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended |
58
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q5_K_S.gguf) | Q5_K_S | 5.8 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q5_K_M.gguf) | Q5_K_M | 6.0 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q6_K.gguf) | Q6_K | 6.8 | very good quality |
 
 
61
 
62
  Here is a handy graph by ikawrakow comparing some lower-quality quant
63
  types (lower is better):
 
52
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q2_K.gguf) | Q2_K | 3.4 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q3_K_S.gguf) | Q3_K_S | 3.9 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q3_K_L.gguf) | Q3_K_L | 4.5 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.IQ4_XS.gguf) | IQ4_XS | 4.7 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended |
58
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended |
59
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q5_K_S.gguf) | Q5_K_S | 5.8 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q5_K_M.gguf) | Q5_K_M | 6.0 | |
61
  | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q6_K.gguf) | Q6_K | 6.8 | very good quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Doctor-R1-GGUF/resolve/main/Doctor-R1.f16.gguf) | f16 | 16.5 | 16 bpw, overkill |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant
66
  types (lower is better):