← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
404.1
PP tok/s
26.9
TG tok/s
2534
TTFT (ms)
94.0
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 404.1 | 26.9 | 94.0 GB | current |
| 4k | 478.0 | 24.4 | 95.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.9 | 1.00× |
| 2× | 36.7 | 1.36× |
| 4× | 49.3 | 1.83× |
| 8× | 194.2 | 7.22× |