← Back to community benchmarks

Qwen3.5-VL-122B-A10B-4bitCRACK-X

M5 Max (40c) · 128 GB · 4bit · 2026-03-17
Performance
8k
tokens
892.2
PP tok/s
54.4
TG tok/s
9182
TTFT (ms)
67.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.14
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 826.4 59.9 66.3 GB view
4k 866.2 55.5 66.7 GB view
8k 892.2 54.4 67.0 GB current
Batching Results
Batch Size TG tok/s Speedup
59.9 1.00×
81.6 1.36×
99.2 1.66×