← Back to community benchmarks

Qwen3.5-0.8B

M4 (10c) · 16 GB · 8bit · 2026-03-11
Performance
1k
tokens
2,153
PP tok/s
105.0
TG tok/s
476
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.3.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,153 105.0 1.8 GB current
4k 2,117 98.5 1.9 GB view
Batching Results
Batch Size TG tok/s Speedup
105.0 1.00×
196.2 1.87×
325.1 3.10×