← Back to community benchmarks
Qwen3.5-122B-A10B3.7bit-VL
Performance
64k
tokens
619.5
PP tok/s
22.2
TG tok/s
105783
TTFT (ms)
58.9
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
65,536