mradermacher commited on
Commit
f04d981
·
verified ·
1 Parent(s): a5cee62

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -42,7 +42,15 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q2_K.gguf) | Q2_K | 3.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
 
 
 
 
 
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
 
42
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q2_K.gguf) | Q2_K | 3.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.IQ4_XS.gguf) | IQ4_XS | 4.1 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q5_K_S.gguf) | Q5_K_S | 5.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q5_K_M.gguf) | Q5_K_M | 5.3 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q6_K.gguf) | Q6_K | 6.1 | very good quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-Math-Code-GGUF/resolve/main/Olmo-3-7B-Think-Math-Code.f16.gguf) | f16 | 14.7 | 16 bpw, overkill |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):