Alibaba · 80B (3B active) · Mixture of Experts
Ultra-efficient agentic coding MoE optimized for tool-calling coding agents お使いの GPU や Mac で Qwen 3 Coder Next 80B-A3B が動くか確認——最小 44.7 GB、推奨 74.5 GB。
2026-02256K context
Mixture of Experts
エキスパート総数： 512
アクティブなエキスパート： 10
アクティブパラメータ： 3.0B
| 量子化 | ビット | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 26.1 GB | low | — |
| Q3_K_M | 3 | 36.4 GB | moderate | — |
| Q4_K_M | 4 | 41.5 GB | good | — |
| Q5_K_M | 5 | 51.7 GB | good | — |
| Q6_K | 6 | 62 GB | excellent | — |
| Q8_0 | 8 | 82.5 GB | excellent | — |
| F16 | 16 | 164.4 GB | lossless | — |
Can I run Qwen 3 Coder Next 80B-A3B locally?
- Can I run Qwen 3 Coder Next 80B-A3B locally?
- Qwen 3 Coder Next 80B-A3B needs about 44.7 GB of memory at a minimum and 74.5 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Qwen 3 Coder Next 80B-A3B need?
- At Q4_K_M, Qwen 3 Coder Next 80B-A3B uses about 41.5 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.