← Back to community benchmarks

Qwen2.5-7B-Instruct

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
140.0
PP tok/s
14.4
TG tok/s
7314
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 140.0 14.4 4.5 GB current
4k 136.3 13.3 4.8 GB view
Batching Results
Batch Size TG tok/s Speedup
14.4 1.00×
26.9 1.87×
18.5 1.28×