← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
550.5
PP tok/s
56.0
TG tok/s
14880
TTFT (ms)
68.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19.dev3
macOS
macOS 26.3.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 593.8 | 61.9 | 66.4 GB | view |
| 4k | 608.1 | 57.4 | 67.9 GB | view |
| 8k | 550.5 | 56.0 | 68.5 GB | current |
| 16k | 487.7 | 41.4 | 69.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.9 | 1.00× |
| 2× | 70.3 | 1.14× |
| 4× | 102.0 | 1.65× |
| 8× | 141.2 | 2.28× |