Hugging Face's logo

mradermacher
/
Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
0947d7c
•
1 Parent(s): 2a7a3b3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -31,16 +31,26 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
 
34
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
 
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
35
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
44
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-EVA-Instruct-Merge-0.1-i1-GGUF/resolve/main/Qwen2.5-32B-EVA-Instruct-Merge-0.1.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant