← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
491.3
PP tok/s
39.3
TG tok/s
8338
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.8
macOS
macOS 15.7.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 459.2 | 42.7 | 66.3 GB | view |
| 4k | 491.3 | 39.3 | 66.7 GB | current |
| 8k | 433.7 | 38.4 | 67.0 GB | view |
| 16k | 391.2 | 27.2 | 67.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.7 | 1.00× |
| 2× | 42.3 | 0.99× |
| 4× | 75.3 | 1.76× |
| 8× | 70.9 | 1.66× |