← Back to community benchmarks

Qwen2.5-0.5B-Instruct

M1 (7c) · 8 GB · 4bit · 2026-03-13
Performance
1k
tokens
1,412
PP tok/s
127.5
TG tok/s
725
TTFT (ms)
0.9
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 8 GB
GPU Cores 7
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,412 127.5 0.9 GB current
4k 1,362 97.3 1.0 GB view
Batching Results
Batch Size TG tok/s Speedup
127.5 1.00×
158.8 1.25×
168.6 1.32×