← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Max (30c) · 96 GB · 4bit · 2026-03-30
Performance
8k
tokens
330.2
PP tok/s
31.0
TG tok/s
24813
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.3.0rc1
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 323.5 34.6 65.6 GB view
4k 362.3 33.1 67.0 GB view
8k 330.2 31.0 67.7 GB current
16k 317.0 27.9 68.9 GB view
32k 294.6 23.2 71.2 GB view
64k 220.3 13.8 76.1 GB view