← Back to community benchmarks

Qwen2.5-Coder-7B-Instruct

M1 (7c) · 8 GB · 4bit · 2026-03-11
Performance
4k
tokens
119.1
PP tok/s
13.4
TG tok/s
34379
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 8 GB
GPU Cores 7
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 123.5 14.4 4.5 GB view
4k 119.1 13.4 4.8 GB current
Batching Results
Batch Size TG tok/s Speedup
14.4 1.00×
24.5 1.70×
22.6 1.57×