← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M5 Max (40c) · 128 GB · 5bit · 2026-03-27
Performance
32k
tokens
3,602
PP tok/s
44.9
TG tok/s
9098
TTFT (ms)
85.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.22
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 3,521 45.7 85.2 GB view
32k 3,602 44.9 85.9 GB current
64k 3,018 43.3 86.8 GB view