← Back to community benchmarks

Qwen3.5-0.8B

M4 (8c) · 16 GB · unknown · 2026-03-11
Performance
1k
tokens
1,142
PP tok/s
11.7
TG tok/s
897
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,142 11.7 3.4 GB current
4k 1,256 11.3 3.5 GB view
Batching Results
Batch Size TG tok/s Speedup
11.7 1.00×
22.0 1.88×
42.2 3.61×