What hardware runs Nomic Embed Text?

The smallest-memory cataloged machine that runs Nomic Embed Text on the GPU is a AMD Radeon RX 7600 · 8GB VRAM. Here are the rigs that fit it, smallest memory first.

machinebest fitverdictspeed
AMD Radeon RX 7600 · 8GB VRAM 137M F16 ✅ Runs comfortably 410–680 tok/s
Apple M1 · 8GB 137M F16 ✅ Runs comfortably 140–240 tok/s
Apple M2 · 8GB 137M F16 ✅ Runs comfortably 210–350 tok/s
Apple M3 · 8GB 137M F16 ✅ Runs comfortably 210–350 tok/s
NVIDIA GeForce RTX 3070 · 8GB VRAM 137M F16 ✅ Runs comfortably 670–1110 tok/s
NVIDIA GeForce RTX 4060 · 8GB VRAM 137M F16 ✅ Runs comfortably 400–670 tok/s
NVIDIA GeForce RTX 3080 · 10GB VRAM 137M F16 ✅ Runs comfortably 1130–1880 tok/s
AMD Radeon RX 6700 XT · 12GB VRAM 137M F16 ✅ Runs comfortably 540–900 tok/s
AMD Radeon RX 7700 XT · 12GB VRAM 137M F16 ✅ Runs comfortably 610–1020 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM 137M F16 ✅ Runs comfortably 540–890 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM 137M F16 ✅ Runs comfortably 750–1250 tok/s
AMD Radeon RX 6800 XT · 16GB VRAM 137M F16 ✅ Runs comfortably 720–1200 tok/s

Already have a machine? See Nomic Embed Text across popular rigs → or check your exact rig →

Planning a whole workflow? Rigs for a coding agent · local chat · reasoning · local RAG setup.

$npx runlocal-sh can-i-run nomic-embed-text --hardware <your-rig>

Verdicts use the same GQA-aware fit math as the CLI — a AMD Radeon RX 7600 verdict here matches what runlocal tells you on the machine.