← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 256 GB · 6bit · 2026-03-28
User comment1
Performance
1k
tokens
609.5
PP tok/s
47.7
TG tok/s
1680
TTFT (ms)
94.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.24.dev2
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 609.5 47.7 94.0 GB current
4k 713.6 44.2 95.5 GB view
Batching Results
Batch Size TG tok/s Speedup
47.7 1.00×
71.5 1.50×
89.6 1.88×