← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-03-27
Performance
16k
tokens
3,716
PP tok/s
15.3
TG tok/s
4409
TTFT (ms)
72.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.22
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 809.7 15.2 69.9 GB view
4k 1,064 14.9 72.9 GB view
8k 1,058 14.7 74.1 GB view
16k 3,716 15.3 72.2 GB current
Batching Results
Batch Size TG tok/s Speedup
15.2 1.00×
27.8 1.83×
47.0 3.09×