← Back to community benchmarks

Qwen3.5-122B-A10B3.7bit-VL

M1 Max (32c) · 64 GB · 3bit · 2026-03-26
Performance
16k
tokens
709.4
PP tok/s
24.6
TG tok/s
23095
TTFT (ms)
55.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.21
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 188.6 18.8 56.6 GB view
16k 709.4 24.6 55.6 GB current