← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-03-27
Performance
8k
tokens
1,058
PP tok/s
14.7
TG tok/s
7744
TTFT (ms)
74.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.22
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 809.7 15.2 69.9 GB view
4k 1,064 14.9 72.9 GB view
8k 1,058 14.7 74.1 GB current
16k 3,716 15.3 72.2 GB view
Batching Results
Batch Size TG tok/s Speedup
15.2 1.00×
27.8 1.83×
47.0 3.09×