← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
516.1
PP tok/s
55.7
TG tok/s
1984
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 516.1 | 55.7 | 65.6 GB | current |
| 4k | 584.0 | 53.7 | 66.9 GB | view |
| 8k | 577.1 | 49.5 | 67.5 GB | view |
| 16k | 543.4 | 37.9 | 68.7 GB | view |
| 32k | 471.0 | 31.1 | 71.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.7 | 1.00× |
| 2× | 85.0 | 1.53× |
| 4× | 112.0 | 2.01× |
| 8× | 136.4 | 2.45× |