Alibaba · 2.4T (95B active) · Mixture of Experts
Frontier Qwen 3.8 MoE — 95B active, 1M context お使いの GPU や Mac で Qwen 3.8 2.4T-A95B が動くか確認——最小 1341.1 GB、推奨 2235.2 GB。
2026-081024K context
| 量子化 | ビット | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 768.8 GB | low | — |
| Q3_K_M | 3 | 1076.2 GB | moderate | — |
| Q4_K_M | 4 | 1229.8 GB | good | — |
| Q5_K_M | 5 | 1537.2 GB | good | — |
| Q6_K | 6 | 1844.5 GB | excellent | — |
| Q8_0 | 8 | 2459.2 GB | excellent | — |
| F16 | 16 | 4917.9 GB | lossless | — |
Can I run Qwen 3.8 2.4T-A95B locally?
- Can I run Qwen 3.8 2.4T-A95B locally?
- Qwen 3.8 2.4T-A95B needs about 1341.1 GB of memory at a minimum and 2235.2 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 3.8 2.4T-A95B need?
- At Q4_K_M, Qwen 3.8 2.4T-A95B uses about 1229.8 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.