← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M5 Max (40c) · 128 GB · 5bit · 2026-03-27
Performance
16k
tokens
3,521
PP tok/s
45.7
TG tok/s
4653
TTFT (ms)
85.2
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
16k 3,521 45.7 85.2 GB current
32k 3,602 44.9 85.9 GB view
64k 3,018 43.3 86.8 GB view