← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M4 Max (40c) · 128 GB · 4bit · 2026-04-13
Performance
4k
tokens
586.6
PP tok/s
47.7
TG tok/s
6983
TTFT (ms)
69.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 520.4 49.6 68.2 GB view
4k 586.6 47.7 69.5 GB current
8k 577.7 45.6 70.1 GB view
16k 1,466 15.1 71.7 GB view
Batching Results
Batch Size TG tok/s Speedup
49.6 1.00×
74.8 1.51×
89.8 1.81×
108.1 2.18×