← Back to community benchmarks

Qwen3.5-122B-A10B9bit

M3 Ultra (80c) · 512 GB · 6bit · 2026-04-05
Performance
1k
tokens
136.0
PP tok/s
13.4
TG tok/s
7527
TTFT (ms)
191.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.4
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 136.0 13.4 191.7 GB current
4k 168.9 12.9 193.3 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 13.4 1.00×
2× 16.1 1.20×
4× 20.1 1.50×