← Back to community benchmarks

Qwen2.5-1.5B-Instruct

M4 (10c) · 16 GB · unknown · 2026-03-12
Performance
1k
tokens
1,015
PP tok/s
31.5
TG tok/s
1009
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.8
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,015 31.5 3.3 GB current
4k 1,072 30.0 3.5 GB view
Batching Results
Batch Size TG tok/s Speedup
31.5 1.00×
40.3 1.28×
77.4 2.46×