← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 256 GB · 6bit · 2026-03-31
Performance
4k
tokens
735.1
PP tok/s
41.9
TG tok/s
5572
TTFT (ms)
96.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.19
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 678.7 43.6 94.9 GB view
4k 735.1 41.9 96.3 GB current
8k 721.9 39.5 96.9 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 43.6 1.00×
2× 66.4 1.52×
4× 89.4 2.05×