Hugging Face's logo

mradermacher
/
Qwen2.5-14B-Instruct-i1-GGUF

Transformers
GGUF
English
chat
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
b613d2c
·
verified ·
1 Parent(s): b233459

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -38,6 +38,7 @@ more details, including on how to concatenate multi-part files.
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
@@ -51,10 +52,14 @@ more details, including on how to concatenate multi-part files.
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
 
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
 
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
 
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
 
58
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_0.gguf) | i1-Q5_0 | 10.4 | |
61
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_1.gguf) | i1-Q5_1 | 11.2 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant