← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
521.7
PP tok/s
49.3
TG tok/s
7852
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 519.8 | 52.9 | 66.3 GB | view |
| 4k | 521.7 | 49.3 | 66.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.9 | 1.00× |
| 2× | 79.5 | 1.50× |
| 4× | 82.6 | 1.56× |