← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 8bit · 2026-05-05
Performance
8k
tokens
458.4
PP tok/s
34.6
TG tok/s
17869
TTFT (ms)
89.3
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 8,192
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 current
16k 396.0 32.3 90.5 GB view