← Back to community benchmarks

Qwen3.5-4B

M5 (8c) · 16 GB · 4bit · 2026-04-18
Performance
1k
tokens
834.7
PP tok/s
47.3
TG tok/s
1227
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M5 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 834.7 47.3 3.3 GB current
4k 975.4 43.3 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
47.3 1.00×
85.8 1.81×
98.6 2.08×