← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
16k
tokens
445.4
PP tok/s
33.5
TG tok/s
36785
TTFT (ms)
83.1
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
16,384