← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Max (40c) · 128 GB · 4bit · 2026-03-10
Performance
1k
tokens
486.2
PP tok/s
45.3
TG tok/s
2106
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 486.2 45.3 66.3 GB current
4k 480.1 42.0 66.7 GB view
Batching Results
Batch Size TG tok/s Speedup
45.3 1.00×
56.7 1.25×
73.0 1.61×