mradermacher commited on
Commit
5c6b953
·
verified ·
1 Parent(s): d57c01a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -29,8 +29,29 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
 
 
 
 
 
 
 
 
 
 
34
 
35
  Here is a handy graph by ikawrakow comparing some lower-quality quant
36
  types (lower is better):
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
34
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
40
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
44
  | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/QwQ-32B-ArliAI-RpR-v1-i1-GGUF/resolve/main/QwQ-32B-ArliAI-RpR-v1.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):