← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Max (40c) · 128 GB · 4bit · 2026-03-14
Performance
64k
tokens
143.3
PP tok/s
7.4
TG tok/s
457247
TTFT (ms)
71.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.11
macOS macOS 26.3
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 401.9 41.8 66.3 GB view
64k 143.3 7.4 71.9 GB current
Batching Results
Batch Size TG tok/s Speedup
41.8 1.00×
31.3 0.75×