← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
8k
tokens
1,495
PP tok/s
57.2
TG tok/s
5480
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,013 | 63.1 | 65.6 GB | view |
| 4k | 1,486 | 59.5 | 67.0 GB | view |
| 8k | 1,495 | 57.2 | 67.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.1 | 1.00× |
| 2× | 96.6 | 1.53× |
| 4× | 130.4 | 2.07× |