← Back to community benchmarks

Qwen3.5-4B-OptiQ

M3 Max (40c) · 64 GB · 4bit · 2026-03-15
Performance
1k
tokens
1,025
PP tok/s
96.1
TG tok/s
999
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,025 96.1 4.0 GB current
4k 1,269 91.7 4.1 GB view
Batching Results
Batch Size TG tok/s Speedup
96.1 1.00×
178.5 1.86×
221.7 2.31×