← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-03-27
Performance
1k
tokens
1,274
PP tok/s
58.5
TG tok/s
804
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.20.dev3
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,274 58.5 66.4 GB current
4k 1,409 56.4 67.9 GB view
Batching Results
Batch Size TG tok/s Speedup
58.5 1.00×
93.2 1.59×
123.4 2.11×