Qwen3.6-35B-A3B-NSC-ACE-SABER-8bit-MTPLX-Optimized-Speed

Description

Qwen3.6-35B-A3B-NSC-ACE-SABER-8bit-MTPLX-Optimized-Speed is an open-weight text-generation model with roughly 35B parameters published by samuelfaj on the Hugging Face Hub. It has 312 downloads. Runs with mlx.

Categories

• Productivity

Tags

• qwen3_5_moe
• lightning-mlx
• mtplx
• qwen3.5
• mixture-of-experts
• apple-silicon
• saber
• nsc-ace

Capabilities

• Text generation
• Conversational
• Library: mlx
• 35B parameters