← Back to community benchmarks

Qwen3.5-122B-A10B-Text-qx85

M3 Max (40c) · 128 GB · 8bit · 2026-05-05
Performance
16k
tokens
396.0
PP tok/s
32.3
TG tok/s
41375
TTFT (ms)
90.5
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 419.6 38.7 87.1 GB view
4k 480.3 35.2 88.4 GB view
8k 458.4 34.6 89.3 GB view
16k 396.0 32.3 90.5 GB current