Alibaba · 80B (3B active) · Mixture of Experts
High-sparsity MoE — extreme low activation ratio for fast inference at 80B scale
0 downloads
0 likes
2025-12 256K context
Use Cases
chat reasoning code
Mixture of Experts
Total experts: 512
Active experts: 10
Active params: 3.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| 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 | — |
About this model
High-sparsity MoE — extreme low activation ratio for fast inference at 80B scale