Hugging Face's logo

mradermacher
/
OpenMath-CodeLlama-34b-Python-hf-i1-GGUF

Transformers
GGUF
English
nvidia
code
math
imatrix
Model card Files
xet
 Community
mradermacher commited on
Commit
2752e4a
·
verified ·
1 Parent(s): e774b2d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -35,9 +35,29 @@ more details, including on how to concatenate multi-part files.
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q2_K.gguf) | i1-Q2_K | 12.6 | IQ3_XXS probably better |
 
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 15.3 | |
 
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.3 | optimal size/speed/quality |
 
 
 
 
 
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):
 
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
39
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ2_S.gguf) | i1-IQ2_S | 10.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ2_M.gguf) | i1-IQ2_M | 11.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.7 | very low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q2_K.gguf) | i1-Q2_K | 12.6 | IQ3_XXS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.1 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.7 | IQ3_XS probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ3_S.gguf) | i1-IQ3_S | 14.8 | beats Q3_K* |
50
  | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 15.3 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.4 | IQ3_S probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.9 | IQ3_M probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q4_0.gguf) | i1-Q4_0 | 19.2 | fast, low quality |
55
  | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.3 | optimal size/speed/quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.3 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q4_1.gguf) | i1-Q4_1 | 21.2 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.3 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.9 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-34b-Python-hf-i1-GGUF/resolve/main/OpenMath-CodeLlama-34b-Python-hf.i1-Q6_K.gguf) | i1-Q6_K | 27.8 | practically like static Q6_K |
61
 
62
  Here is a handy graph by ikawrakow comparing some lower-quality quant
63
  types (lower is better):