← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
1,263
PP tok/s
61.8
TG tok/s
811
TTFT (ms)
71.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,263 | 61.8 | 71.1 GB | current |
| 4k | 1,608 | 59.2 | 72.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.8 | 1.00× |
| 2× | 96.4 | 1.56× |
| 4× | 128.7 | 2.08× |