← Back to community benchmarks

Qwen2.5-VL-7B-Instruct

M2 (10c) · 16 GB · 4bit · 2026-04-15
Performance
1k
tokens
199.1
PP tok/s
20.7
TG tok/s
5144
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.5
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 199.1 20.7 4.5 GB current
4k 193.8 18.0 4.9 GB view
Batching Results
Batch Size TG tok/s Speedup
20.7 1.00×
35.7 1.72×
38.1 1.84×