← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 96 GB · 4bit · 2026-03-12
Performance
4k
tokens
726.9
PP tok/s
53.0
TG tok/s
5635
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 651.0 55.6 66.3 GB view
4k 726.9 53.0 66.7 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 55.6 1.00×
2× 90.0 1.62×
4× 127.7 2.30×
8× 170.6 3.07×