← Back to community benchmarks
Qwen3.5-122B-A10B-oQ3.5
Performance
8k
tokens
552.9
PP tok/s
46.2
TG tok/s
14816
TTFT (ms)
61.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 4k | 276.8 | 49.0 | 60.5 GB | view |
| 8k | 552.9 | 46.2 | 61.1 GB | current |