← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
4k
tokens
198.1
PP tok/s
31.7
TG tok/s
20674
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.12
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 226.9 | 35.0 | 66.3 GB | view |
| 4k | 198.1 | 31.7 | 66.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.0 | 1.00× |
| 2× | 39.5 | 1.13× |
| 4× | 42.1 | 1.20× |