88plug/Qwen3.6-35B-A3B-W8A16
Image-Text-to-Text • 35B • Updated • 776 • 3
88plug W8A16 Quantizations
INT8 weight-only (W8A16) compressed-tensors quantizations. BF16 activations. Native vLLM compressed-tensors.
-
-
88plug/Qwen3.6-27B-W8A16
Image-Text-to-Text • 27B • Updated • 6.61k • 2 -
88plug/Qwen3-Omni-30B-A3B-W8A16
Text Generation • 35B • Updated • 714 -
88plug/Qwen2.5-Omni-7B-W8A16
Text Generation • 11B • Updated • 771 -
88plug/Gemma4-E4B-it-W8A16
Image-Text-to-Text • 9B • Updated • 236 -
88plug/Gemma4-E2B-it-W8A16
Image-Text-to-Text • 5B • Updated • 259 -
88plug/MiniCPM-o-4.5-W8A16
Image-Text-to-Text • 9B • Updated • 192 -
88plug/Nemotron-3-Nano-30B-A3B-W8A16
Text Generation • 32B • Updated • 1.36k -
88plug/Kimi-VL-A3B-Thinking-2506-W8A16
Image-Text-to-Text • 17B • Updated • 222