Hugging Face's logo

mradermacher
/
Qwen2.5-14b-web-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
1566fc8
·
verified ·
1 Parent(s): f9e4db5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -37,15 +37,21 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.6 | fast on arm, low quality |
 
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.6 | fast on arm, low quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14b-web-i1-GGUF/resolve/main/Qwen2.5-14b-web.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant