← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-04-02
Performance
195k
tokens
376.5
PP tok/s
11.5
TG tok/s
531251
TTFT (ms)
95.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.0
macOS macOS 26.4
Context 200,000