← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
572.1
PP tok/s
52.1
TG tok/s
7160
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 15.6.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 554.3 | 54.6 | 66.3 GB | view |
| 4k | 572.1 | 52.1 | 66.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.6 | 1.00× |
| 2× | 88.2 | 1.62× |
| 4× | 117.4 | 2.15× |
| 8× | 139.1 | 2.55× |