Hugging Face's logo

mradermacher
/
NuminaMath-72B-CoT-GGUF

Transformers
GGUF
English
math
aimo
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
6aee4c3
·
verified ·
1 Parent(s): 0b648b1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -36,7 +36,15 @@ more details, including on how to concatenate multi-part files.
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
  | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q2_K.gguf) | Q2_K | 29.9 | |
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
 
 
 
 
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
  | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q2_K.gguf) | Q2_K | 29.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q3_K_S.gguf) | Q3_K_S | 34.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q3_K_L.gguf) | Q3_K_L | 39.6 | |
42
  | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended |
44
+ | [PART 1](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
46
+ | [PART 1](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
47
+ | [PART 1](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NuminaMath-72B-CoT-GGUF/resolve/main/NuminaMath-72B-CoT.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):