AI & ML interests
We're a trio of AI enthusiasts who create LLM quantization models (GPTQ, WNA16) in our spare time. We bridge ModelScope and Hugging Face by porting our quantized models to make efficient AI more accessible globally.
Recent Activity
View all activity
-
QuantTrio/DeepSeek-V3.2-Speciale-AWQ
Text Generation • 685B • Updated • 26 • 4 -
QuantTrio/DeepSeek-V3.2-AWQ
Text Generation • 685B • Updated • 498k • 11 -
QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite
Text Generation • 685B • Updated • 18 • 4 -
QuantTrio/DeepSeek-V3.2-Exp-AWQ
Text Generation • 685B • Updated • 131 • 4
-
QuantTrio/Qwen3-VL-235B-A22B-Instruct-AWQ
Text Generation • 236B • Updated • 2.07k • 13 -
QuantTrio/Qwen3-VL-235B-A22B-Instruct-FP8
Text Generation • Updated • 23 -
QuantTrio/Qwen3-VL-235B-A22B-Thinking-AWQ
Text Generation • 236B • Updated • 1.27k • 8 -
QuantTrio/Qwen3-VL-235B-A22B-Thinking-FP8
Text Generation • 236B • Updated • 25
-
QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix
Text Generation • 20B • Updated • 9.06k • 10 -
QuantTrio/GLM-4.5-Air-AWQ-FP16Mix
Text Generation • 24B • Updated • 1.48k • 14 -
QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix
Text Generation • 55B • Updated • 50 • 5 -
QuantTrio/GLM-4.5-AWQ
Text Generation • 53B • Updated • 31 • 9
-
Qwen/Qwen3-Coder-480B-A35B-Instruct
Text Generation • 480B • Updated • 44k • • 1.34k -
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Text Generation • 480B • Updated • 144k • 156 -
QuantTrio/Qwen3-Coder-480B-A35B-Instruct-AWQ
Text Generation • 480B • Updated • 2.5k • 8 -
QuantTrio/Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix
Text Generation • 534B • Updated • 114 • 8
awq quantization
-
QuantTrio/Qwen3.5-35B-A3B-AWQ
Image-Text-to-Text • 36B • Updated • 88.6k • 18 -
QuantTrio/Qwen3.5-122B-A10B-AWQ
Image-Text-to-Text • 125B • Updated • 13.9k • 28 -
QuantTrio/Qwen3.5-397B-A17B-AWQ
Image-Text-to-Text • Updated • 10.4k • 9 -
QuantTrio/Qwen3.5-27B-AWQ
Image-Text-to-Text • 28B • Updated • 260k • 43
-
QuantTrio/Seed-OSS-36B-Instruct-AWQ
Text Generation • 36B • Updated • 260 • 8 -
QuantTrio/Seed-OSS-36B-Instruct-GPTQ-Int3
Text Generation • 34B • Updated • 8 • 3 -
QuantTrio/Seed-OSS-36B-Instruct-GPTQ-Int4
Text Generation • 36B • Updated • 15 • 5 -
QuantTrio/Seed-OSS-36B-Instruct-GPTQ-Int8
Text Generation • 36B • Updated • 39 • 4
-
QuantTrio/Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix
Text Generation • 248B • Updated • 133 • 4 -
QuantTrio/Qwen3-235B-A22B-Instruct-2507-AWQ
Text Generation • 235B • Updated • 14.3k • 11 -
QuantTrio/Qwen3-235B-A22B-Thinking-2507-GPTQ-Int4-Int8Mix
Text Generation • 253B • Updated • 27 • 4 -
QuantTrio/Qwen3-235B-A22B-Thinking-2507-AWQ
Text Generation • 235B • Updated • 610 • 6
awq quantization
-
QuantTrio/Qwen3.5-35B-A3B-AWQ
Image-Text-to-Text • 36B • Updated • 88.6k • 18 -
QuantTrio/Qwen3.5-122B-A10B-AWQ
Image-Text-to-Text • 125B • Updated • 13.9k • 28 -
QuantTrio/Qwen3.5-397B-A17B-AWQ
Image-Text-to-Text • Updated • 10.4k • 9 -
QuantTrio/Qwen3.5-27B-AWQ
Image-Text-to-Text • 28B • Updated • 260k • 43
-
QuantTrio/DeepSeek-V3.2-Speciale-AWQ
Text Generation • 685B • Updated • 26 • 4 -
QuantTrio/DeepSeek-V3.2-AWQ
Text Generation • 685B • Updated • 498k • 11 -
QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite
Text Generation • 685B • Updated • 18 • 4 -
QuantTrio/DeepSeek-V3.2-Exp-AWQ
Text Generation • 685B • Updated • 131 • 4
-
QuantTrio/Qwen3-VL-235B-A22B-Instruct-AWQ
Text Generation • 236B • Updated • 2.07k • 13 -
QuantTrio/Qwen3-VL-235B-A22B-Instruct-FP8
Text Generation • Updated • 23 -
QuantTrio/Qwen3-VL-235B-A22B-Thinking-AWQ
Text Generation • 236B • Updated • 1.27k • 8 -
QuantTrio/Qwen3-VL-235B-A22B-Thinking-FP8
Text Generation • 236B • Updated • 25
-
QuantTrio/Seed-OSS-36B-Instruct-AWQ
Text Generation • 36B • Updated • 260 • 8 -
QuantTrio/Seed-OSS-36B-Instruct-GPTQ-Int3
Text Generation • 34B • Updated • 8 • 3 -
QuantTrio/Seed-OSS-36B-Instruct-GPTQ-Int4
Text Generation • 36B • Updated • 15 • 5 -
QuantTrio/Seed-OSS-36B-Instruct-GPTQ-Int8
Text Generation • 36B • Updated • 39 • 4
-
QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix
Text Generation • 20B • Updated • 9.06k • 10 -
QuantTrio/GLM-4.5-Air-AWQ-FP16Mix
Text Generation • 24B • Updated • 1.48k • 14 -
QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix
Text Generation • 55B • Updated • 50 • 5 -
QuantTrio/GLM-4.5-AWQ
Text Generation • 53B • Updated • 31 • 9
-
QuantTrio/Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix
Text Generation • 248B • Updated • 133 • 4 -
QuantTrio/Qwen3-235B-A22B-Instruct-2507-AWQ
Text Generation • 235B • Updated • 14.3k • 11 -
QuantTrio/Qwen3-235B-A22B-Thinking-2507-GPTQ-Int4-Int8Mix
Text Generation • 253B • Updated • 27 • 4 -
QuantTrio/Qwen3-235B-A22B-Thinking-2507-AWQ
Text Generation • 235B • Updated • 610 • 6
-
Qwen/Qwen3-Coder-480B-A35B-Instruct
Text Generation • 480B • Updated • 44k • • 1.34k -
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Text Generation • 480B • Updated • 144k • 156 -
QuantTrio/Qwen3-Coder-480B-A35B-Instruct-AWQ
Text Generation • 480B • Updated • 2.5k • 8 -
QuantTrio/Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix
Text Generation • 534B • Updated • 114 • 8