← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-17
Performance
4k
tokens
1,616
PP tok/s
59.6
TG tok/s
2534
TTFT (ms)
67.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.16
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,268 62.1 66.4 GB view
4k 1,616 59.6 67.9 GB current
8k 1,542 56.8 68.5 GB view
16k 1,290 41.8 69.7 GB view
Batching Results
Batch Size TG tok/s Speedup
62.1 1.00×
83.0 1.34×
109.9 1.77×
162.2 2.61×