← Back to community benchmarks

Qwen3.5-0.8B

M3 Pro (14c) · 18 GB · 8bit · 2026-03-11
Performance
1k
tokens
2,768
PP tok/s
130.1
TG tok/s
370
TTFT (ms)
2.0
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 18 GB
GPU Cores 14
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 130.1 1.00×
2× 231.4 1.78×
4× 339.6 2.61×
8× 367.5 2.82×