← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M5 Max (40c) · 128 GB · 5bit · 2026-03-28
Performance
16k
tokens
1,158
PP tok/s
37.3
TG tok/s
14145
TTFT (ms)
83.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.24.dev2
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,516 45.3 82.1 GB view
8k 1,344 42.9 82.7 GB view
16k 1,158 37.3 83.9 GB current
32k 1,004 29.3 86.3 GB view