← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-03-26
Performance
32k
tokens
3,550
PP tok/s
15.0
TG tok/s
9231
TTFT (ms)
73.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.20
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 820.7 16.4 69.9 GB view
4k 1,070 15.9 72.9 GB view
8k 1,045 16.0 74.1 GB view
16k 3,441 16.3 72.2 GB view
32k 3,550 15.0 73.5 GB current
Batching Results
Batch Size TG tok/s Speedup
16.4 1.00×
30.0 1.83×