← Back to community benchmarks

Qwen3.5-0.8B

M4 (8c) · 16 GB · 8bit · 2026-03-09
Performance
1k
tokens
1,768
PP tok/s
101.8
TG tok/s
579
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 15.6
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,768 101.8 1.8 GB current
4k 1,737 98.1 1.9 GB view
8k 1,642 88.6 2.0 GB view
Batching Results
Batch Size TG tok/s Speedup
101.8 1.00×
200.6 1.97×
261.3 2.57×
268.7 2.64×