← Back to community benchmarks

community--Qwen3.5-122B-A10B

M2 Ultra (60c) · 128 GB · 4bit · 2026-03-11
Performance
1k
tokens
327.2
PP tok/s
46.2
TG tok/s
3130
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 128 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 327.2 46.2 66.3 GB current
4k 365.6 44.1 66.7 GB view
8k 368.6 39.4 67.0 GB view
Batching Results
Batch Size TG tok/s Speedup
46.2 1.00×
67.6 1.46×