← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 3bit · 2026-03-26
Performance
8k
tokens
186.0
PP tok/s
18.5
TG tok/s
44035
TTFT (ms)
55.9
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 8,192