Hugging Face's logo

mradermacher
/
Math-AI-Full-GGUF

Transformers
GGUF
English
Hindi
text-generation-inference
qwen3_5
hindi
science in hindi
science
indian languages
maths in hindi
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
b6acb2d
·
verified ·
1 Parent(s): da4a49f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -49,6 +49,18 @@ more details, including on how to concatenate multi-part files.
49
  |:-----|:-----|--------:|:------|
50
  | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement |
51
  | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.mmproj-f16.gguf) | mmproj-f16 | 0.8 | multi-modal supplement |
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
 
49
  |:-----|:-----|--------:|:------|
50
  | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement |
51
  | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.mmproj-f16.gguf) | mmproj-f16 | 0.8 | multi-modal supplement |
52
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q2_K.gguf) | Q2_K | 2.0 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q3_K_S.gguf) | Q3_K_S | 2.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q3_K_L.gguf) | Q3_K_L | 2.5 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.IQ4_XS.gguf) | IQ4_XS | 2.6 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended |
58
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended |
59
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q5_K_S.gguf) | Q5_K_S | 3.1 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q5_K_M.gguf) | Q5_K_M | 3.2 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q6_K.gguf) | Q6_K | 3.6 | very good quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.Q8_0.gguf) | Q8_0 | 4.6 | fast, best quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Math-AI-Full-GGUF/resolve/main/Math-AI-Full.f16.gguf) | f16 | 8.5 | 16 bpw, overkill |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant
66
  types (lower is better):