← Back to community benchmarks

Qwen2.5-0.5B-Instruct

M3 (10c) · 16 GB · unknown · 2026-03-11
Performance
1k
tokens
2,008
PP tok/s
70.1
TG tok/s
510
TTFT (ms)
1.3
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 16 GB
GPU Cores 10
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 2,008 70.1 1.3 GB current
4k 2,479 68.9 1.5 GB view
Batching Results
Batch Size TG tok/s Speedup
70.1 1.00×
81.7 1.17×
184.8 2.64×