Name: Qwen3 Next 80b A3b Thinking - GGUF Model (4 parts)
License: Not specified

10.5K

❤️ 82

Qwen3 Next 80b A3b Thinking

Quantization: BF16 File Size: 672.0 GB · 4 parts Capability: Multi-Model (MoE) License: Not specified Upload Date: November 28, 2025

System Requirements

🖥️

CPU 12+ cores

💾

RAM 1344+ GB

🎮

GPU Recommended

⚠️ High-end hardware required

Download 4 Parts Hugging Face

Copy All Parts Links (4)

https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF/resolve/main/BF16/Qwen3-Next-80B-A3B-Thinking-BF16-00001-of-00004.gguf
https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF/resolve/main/BF16/Qwen3-Next-80B-A3B-Thinking-BF16-00002-of-00004.gguf
https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF/resolve/main/BF16/Qwen3-Next-80B-A3B-Thinking-BF16-00003-of-00004.gguf
https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF/resolve/main/BF16/Qwen3-Next-80B-A3B-Thinking-BF16-00004-of-00004.gguf

Select all (Ctrl+A / Cmd+A) then copy, or browse the BF16 folder on Hugging Face.

Pre-rendered page for Qwen3 Next 80b A3b Thinking. View in full site | Browse all models