← Back to community benchmarks

Qwen3.5-122B-A10B

M4 Max (40c) · 128 GB · 4bit · 2026-03-14
Performance
8k
tokens
563.5
PP tok/s
50.2
TG tok/s
14536
TTFT (ms)
67.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.11
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 549.2 55.5 66.3 GB view
4k 575.2 53.1 66.7 GB view
8k 563.5 50.2 67.0 GB current
16k 531.4 36.0 67.7 GB view
Batching Results
Batch Size TG tok/s Speedup
55.5 1.00×
86.5 1.56×
114.9 2.07×
145.3 2.62×