← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
544.4
PP tok/s
55.9
TG tok/s
1881
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 544.4 | 55.9 | 66.4 GB | current |
| 4k | 597.1 | 53.0 | 67.9 GB | view |
| 8k | 584.6 | 49.9 | 68.5 GB | view |
| 16k | 549.4 | 41.6 | 69.7 GB | view |
| 32k | 483.5 | 33.7 | 72.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.9 | 1.00× |
| 2× | 85.1 | 1.52× |
| 4× | 111.9 | 2.00× |
| 8× | 136.8 | 2.45× |