← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Max (40c) · 128 GB · 4bit · 2026-03-14
User comment参数调整后
Performance
64k
tokens
144.7
PP tok/s
11.8
TG tok/s
453008
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 475.3 42.3 66.3 GB view
64k 144.7 11.8 71.9 GB current
Batching Results
Batch Size TG tok/s Speedup
42.3 1.00×
35.9 0.85×
42.6 1.01×