← Back to community benchmarks

Qwen3.5-122B-A10B-oQ5

M2 Ultra (76c) · 128 GB · 5bit · 2026-03-26
Performance
4k
tokens
437.8
PP tok/s
27.6
TG tok/s
9356
TTFT (ms)
83.5
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 128 GB
GPU Cores 76
Software
oMLX v0.2.21
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 403.8 29.9 82.1 GB view
4k 437.8 27.6 83.5 GB current
8k 436.6 26.0 84.1 GB view
16k 439.7 24.8 85.3 GB view