← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 4bit · 2026-04-16
Performance
4k
tokens
498.5
PP tok/s
42.2
TG tok/s
8217
TTFT (ms)
66.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 15.6.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 437.4 43.9 65.6 GB view
4k 498.5 42.2 66.9 GB current
8k 481.5 39.7 67.5 GB view
Batching Results
Batch Size TG tok/s Speedup
43.9 1.00×
67.9 1.55×
91.9 2.09×
94.0 2.14×