Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-PrismaQuant-8bit-vllm

Description

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-PrismaQuant-8bit-vllm is an open-weight text-generation model with roughly 35B parameters published by cyburn on the Hugging Face Hub. It has 273 downloads.

Categories

• Research
• Productivity
• Design

Tags

• qwen3_5_moe
• quantized
• vllm
• compressed-tensors
• nvfp4
• mxfp8
• mixed-precision
• reasoning

Capabilities

• Text generation
• Conversational
• 35B parameters