← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 4bit · 2026-03-31
Performance
128k
tokens
118.9
PP tok/s
7.6
TG tok/s
1102273
TTFT (ms)
85.7
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.0
macOS macOS 26.4
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 414.9 43.7 65.6 GB view
4k 470.4 40.4 67.0 GB view
8k 411.3 36.3 67.7 GB view
16k 360.8 33.1 68.9 GB view
32k 309.2 23.2 71.2 GB view
64k 140.1 12.1 76.1 GB view
128k 118.9 7.6 85.7 GB current
Batching Results
Batch Size TG tok/s Speedup
43.7 1.00×
34.6 0.79×
41.7 0.95×