← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
486.2
PP tok/s
44.8
TG tok/s
2106
TTFT (ms)
94.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 486.2 | 44.8 | 94.0 GB | current |
| 4k | 560.5 | 42.6 | 95.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.8 | 1.00× |
| 2× | 64.6 | 1.44× |
| 4× | 75.4 | 1.68× |