← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
32k
tokens
461.7
PP tok/s
33.9
TG tok/s
70969
TTFT (ms)
85.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
32,768