← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-20
Performance
16k
tokens
1,203
PP tok/s
48.3
TG tok/s
13620
TTFT (ms)
69.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.19
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,275 61.2 66.4 GB view
4k 1,515 59.5 67.9 GB view
8k 1,412 56.5 68.5 GB view
16k 1,203 48.3 69.7 GB current
Batching Results
Batch Size TG tok/s Speedup
61.2 1.00×
91.5 1.50×
99.4 1.62×
123.3 2.01×