← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
461.8
PP tok/s
37.5
TG tok/s
8870
TTFT (ms)
96.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.20
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 412.3 | 40.1 | 94.9 GB | view |
| 4k | 461.8 | 37.5 | 96.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.1 | 1.00× |
| 2× | 62.0 | 1.55× |
| 4× | 80.4 | 2.00× |