← Back to community benchmarks

Qwen3.5-0.8B

M4 Pro (20c) · 64 GB · 8bit · 2026-03-10
Performance
1k
tokens
4,364
PP tok/s
208.7
TG tok/s
235
TTFT (ms)
2.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 15.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 4,364 208.7 2.0 GB current
4k 4,259 196.9 2.2 GB view
Batching Results
Batch Size TG tok/s Speedup
208.7 1.00×
381.8 1.83×
567.3 2.72×