← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M3 Max (40c) · 128 GB · 5bit · 2026-04-04
Performance
8k
tokens
479.6
PP tok/s
37.3
TG tok/s
17082
TTFT (ms)
81.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.2
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 479.6 37.3 81.9 GB current
16k 424.7 33.7 83.1 GB view