← Back to community benchmarks

Qwen3.5-2B

M4 Pro (20c) · 24 GB · 8bit · 2026-03-16
Performance
1k
tokens
1,970
PP tok/s
106.3
TG tok/s
520
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 24 GB
GPU Cores 20
Software
oMLX v0.2.13
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,970 106.3 3.4 GB current
4k 2,058 102.4 3.6 GB view
8k 2,025 98.7 3.6 GB view
Batching Results
Batch Size TG tok/s Speedup
106.3 1.00×
201.8 1.90×
277.1 2.61×
303.0 2.85×