← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-01
Performance
16k
tokens
1,175
PP tok/s
46.1
TG tok/s
13941
TTFT (ms)
70.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.0
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,021 57.9 66.9 GB view
4k 1,412 55.7 68.2 GB view
16k 1,175 46.1 70.0 GB current
64k 777.7 28.5 77.2 GB view