← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (80c) · 256 GB · 8bit · 2026-03-09
Performance
4k
tokens
911.3
PP tok/s
41.4
TG tok/s
4495
TTFT (ms)
123.5
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 256 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 863.0 42.9 123.2 GB view
4k 911.3 41.4 123.5 GB current
Batching Results
Batch Size TG tok/s Speedup
42.9 1.00×
70.9 1.65×
98.5 2.30×