Hugging Face's logo

mradermacher
/
Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF

Transformers
GGUF
English
Merge
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
mixture of experts
qwen2moe
6X7B
shared expert
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
2b80cb0
·
verified ·
1 Parent(s): 6c5c218

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -51,20 +51,28 @@ more details, including on how to concatenate multi-part files.
51
 
52
  | Link | Type | Size/GB | Notes |
53
  |:-----|:-----|--------:|:------|
 
54
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ1_M.gguf) | i1-IQ1_M | 9.7 | mostly desperate |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.2 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.5 | |
 
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_M.gguf) | i1-IQ2_M | 13.9 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.5 | very low quality |
59
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q2_K.gguf) | i1-Q2_K | 15.5 | IQ3_XXS probably better |
60
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 16.3 | lower quality |
 
61
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.3 | IQ3_XS probably better |
 
62
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ3_M.gguf) | i1-IQ3_M | 18.5 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.2 | IQ3_S probably better |
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q3_K_L.gguf) | i1-Q3_K_L | 21.8 | IQ3_M probably better |
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.5 | |
 
66
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.0 | optimal size/speed/quality |
67
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q4_K_M.gguf) | i1-Q4_K_M | 25.5 | fast, recommended |
 
 
 
68
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q6_K.gguf) | i1-Q6_K | 34.4 | practically like static Q6_K |
69
 
70
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
51
 
52
  | Link | Type | Size/GB | Notes |
53
  |:-----|:-----|--------:|:------|
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ1_S.gguf) | i1-IQ1_S | 8.8 | for the desperate |
55
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ1_M.gguf) | i1-IQ1_M | 9.7 | mostly desperate |
56
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.2 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.5 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_S.gguf) | i1-IQ2_S | 12.7 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ2_M.gguf) | i1-IQ2_M | 13.9 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.5 | very low quality |
61
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q2_K.gguf) | i1-Q2_K | 15.5 | IQ3_XXS probably better |
62
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 16.3 | lower quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ3_XS.gguf) | i1-IQ3_XS | 17.4 | |
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.3 | IQ3_XS probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ3_S.gguf) | i1-IQ3_S | 18.3 | beats Q3_K* |
66
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ3_M.gguf) | i1-IQ3_M | 18.5 | |
67
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.2 | IQ3_S probably better |
68
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q3_K_L.gguf) | i1-Q3_K_L | 21.8 | IQ3_M probably better |
69
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.5 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q4_0.gguf) | i1-Q4_0 | 23.9 | fast, low quality |
71
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.0 | optimal size/speed/quality |
72
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q4_K_M.gguf) | i1-Q4_K_M | 25.5 | fast, recommended |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q4_1.gguf) | i1-Q4_1 | 26.4 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q5_K_S.gguf) | i1-Q5_K_S | 28.9 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q5_K_M.gguf) | i1-Q5_K_M | 29.8 | |
76
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx-i1-GGUF/resolve/main/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-128k-ctx.i1-Q6_K.gguf) | i1-Q6_K | 34.4 | practically like static Q6_K |
77
 
78
  Here is a handy graph by ikawrakow comparing some lower-quality quant