What hardware runs a local coding agent workflow?

A code-generation model plus a small embedder for repo indexing. The smallest cataloged machine that runs Qwen2.5-Coder + Nomic Embed Text is a Apple M1 · 8GB. Ranked below, smallest memory first — each model at its best quant, one model loaded at a time.

machine	Qwen2.5-Coder	Nomic Embed Text
Apple M1 · 8GB	1.5B @ Q8_0 · ~25–45 tok/s	137M @ F16 · ~140–240 tok/s
Apple M2 · 8GB	1.5B @ Q8_0 · ~40–65 tok/s	137M @ F16 · ~210–350 tok/s
Apple M3 · 8GB	1.5B @ Q8_0 · ~40–65 tok/s	137M @ F16 · ~210–350 tok/s
AMD Radeon RX 7600 · 8GB VRAM	7B @ Q6_K · ~18–30 tok/s	137M @ F16 · ~410–680 tok/s
NVIDIA GeForce RTX 3070 · 8GB VRAM	7B @ Q6_K · ~30–50 tok/s	137M @ F16 · ~670–1110 tok/s
NVIDIA GeForce RTX 4060 · 8GB VRAM	7B @ Q6_K · ~18–30 tok/s	137M @ F16 · ~400–670 tok/s
NVIDIA GeForce RTX 3080 · 10GB VRAM	14B @ Q3_K_M · ~45–70 tok/s	137M @ F16 · ~1130–1880 tok/s
AMD Radeon RX 6700 XT · 12GB VRAM	14B @ Q4_K_M · ~17–30 tok/s	137M @ F16 · ~540–900 tok/s
AMD Radeon RX 7700 XT · 12GB VRAM	14B @ Q4_K_M · ~19–30 tok/s	137M @ F16 · ~610–1020 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	14B @ Q4_K_M · ~16–25 tok/s	137M @ F16 · ~540–890 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	14B @ Q4_K_M · ~25–40 tok/s	137M @ F16 · ~750–1250 tok/s
AMD Radeon RX 6800 XT · 16GB VRAM	14B @ Q5_K_M · ~19–30 tok/s	137M @ F16 · ~720–1200 tok/s

Fits computed by the same engine as the CLI — reproduce this table with:

$npx runlocal-sh advise qwen2.5-coder, nomic-embed-text

Already have a machine? Check your exact rig →