← Back to community benchmarks
Qwen3.5-122B-A10B-Text-qx64-hi
Performance
16k
tokens
423.3
PP tok/s
35.0
TG tok/s
38703
TTFT (ms)
90.0
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384