lapo/ qwen3.6:27b-coding-int4

465 1 month ago

Quantized int4 for faster inference and with low temperature for coding.

vision tools thinking
... /
json
7768af27c1fa · 385B
{
"size": {
"longest_edge": 25165824,
"shortest_edge": 4096
},
"patch_size": 16,
"temporal_patch_size": 2,
"merge_size": 2,
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"processor_class": "Qwen3VLProcessor",
"video_processor_type": "Qwen3VLVideoProcessor"
}