← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-10
Performance
64k
tokens
582.9
PP tok/s
23.7
TG tok/s
112433
TTFT (ms)
128.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.7
macOS macOS 26.3
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 857.2 40.4 123.2 GB view
4k 910.7 39.5 123.5 GB view
64k 582.9 23.7 128.7 GB current
Batching Results
Batch Size TG tok/s Speedup
40.4 1.00×
64.9 1.61×
91.3 2.26×
187.5 4.64×