← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-04-05
Performance
16k
tokens
3,147
PP tok/s
18.1
TG tok/s
5207
TTFT (ms)
70.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.2
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 971.2 65.9 66.6 GB view
4k 1,485 63.0 68.0 GB view
8k 1,551 60.1 68.6 GB view
16k 3,147 18.1 70.2 GB current
32k 3,215 18.0 71.6 GB view
64k 2,792 17.4 73.4 GB view
128k 2,126 16.9 76.9 GB view
Batching Results
Batch Size TG tok/s Speedup
65.9 1.00×
100.7 1.53×
129.9 1.97×
155.7 2.36×