← Back to community benchmarks

Qwen3.5-0.8B

M2 Pro (16c) · 32 GB · unknown · 2026-03-11
Performance
4k
tokens
2,387
PP tok/s
23.3
TG tok/s
1716
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.7
macOS macOS 15.7.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,960 23.8 3.5 GB view
4k 2,387 23.3 3.8 GB current
Batching Results
Batch Size TG tok/s Speedup
23.8 1.00×
33.8 1.42×
40.1 1.68×