Qwen3-Next-80B-A3B-Thinking-4bit
mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
80B
Weights (est.)
≈ 44.8 GB
Mac memory (est.)
64 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-Next-80B-A3B-Thinking (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 626 in the last 30 days · 101K all time · 4 likes
- Published
- 2025-09-13 · updated 2025-09-13 (1y ago)
- Tags
- qwen3_next
Other MLX builds of Qwen/Qwen3-Next-80B-A3B-Thinking
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-Next-80B-A3B-Thinking-4bit (this one) | 4-bit | ≈ 44.8 GB | 64 GB+ | 626 |
| Qwen3-Next-80B-A3B-Thinking-5bit | 5-bit | ≈ 54.8 GB | 64 GB+ | 41 |
| Qwen3-Next-80B-A3B-Thinking-6bit | 6-bit | ≈ 64.7 GB | 96 GB+ | 58 |
| Qwen3-Next-80B-A3B-Thinking-8bit | 8-bit | ≈ 84.7 GB | 128 GB+ | 349 |