← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 256 GB · 8bit · 2026-03-20
Performance
8k
tokens
727.3
PP tok/s
37.9
TG tok/s
11263
TTFT (ms)
125.4
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.18
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 676.1 41.9 123.3 GB view
4k 740.9 39.1 124.8 GB view
8k 727.3 37.9 125.4 GB current
Batching Results
Batch Size TG tok/s Speedup
41.9 1.00×
64.2 1.53×
91.9 2.19×