← Back to community benchmarks
Qwen3-Next-80B-A3B-Instruct
Performance
1k
tokens
830.8
PP tok/s
60.1
TG tok/s
1233
TTFT (ms)
61.6
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 830.8 | 60.1 | 61.6 GB | current |
| 4k | 1,050 | 57.4 | 61.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.1 | 1.00× |
| 2× | 94.3 | 1.57× |
| 4× | 119.1 | 1.98× |