srswti/Qwen3-Next-80B-A3B-Thinking-8bit
Text Generation • 80B • Updated • 10
Qwen3 Next
Runs 80B intelligence at 3B compute footprint with 10x faster inference.
-
-
srswti/Qwen3-Next-80B-A3B-Thinking-6bit
Text Generation • 80B • Updated • 17 -
srswti/Qwen3-Next-80B-A3B-Thinking-4bit
Text Generation • 80B • Updated • 20 -
srswti/Qwen3-Next-80B-A3B-Instruct-8bit
Text Generation • 80B • Updated • 19 -
srswti/Qwen3-Next-80B-A3B-Instruct-6bit
Text Generation • 80B • Updated • 25