← Back to community benchmarks

Qwen3.5-0.8B

M4 Pro (20c) · 48 GB · 8bit · 2026-04-29
Performance
4k
tokens
3,719
PP tok/s
200.5
TG tok/s
1101
TTFT (ms)
2.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,455 216.7 1.9 GB view
4k 3,719 200.5 2.1 GB current
8k 3,797 190.8 2.3 GB view
16k 3,643 165.2 2.9 GB view
Batching Results
Batch Size TG tok/s Speedup
216.7 1.00×
382.9 1.77×
532.9 2.46×
610.4 2.82×