← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
1,490
PP tok/s
62.3
TG tok/s
2750
TTFT (ms)
67.0
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.1
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 967.8 | 65.5 | 65.6 GB | view |
| 4k | 1,490 | 62.3 | 67.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.5 | 1.00× |
| 2× | 100.8 | 1.54× |
| 4× | 137.3 | 2.10× |