What hardware runs mxbai-embed-large?

The smallest-memory cataloged machine that runs mxbai-embed-large 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 335M F16 ✅ Runs comfortably 170–280 tok/s
Apple M1 · 8GB 335M F16 ✅ Runs comfortably 60–100 tok/s
Apple M2 · 8GB 335M F16 ✅ Runs comfortably 85–140 tok/s
Apple M3 · 8GB 335M F16 ✅ Runs comfortably 85–140 tok/s
NVIDIA GeForce RTX 3070 · 8GB VRAM 335M F16 ✅ Runs comfortably 270–450 tok/s
NVIDIA GeForce RTX 4060 · 8GB VRAM 335M F16 ✅ Runs comfortably 160–270 tok/s
NVIDIA GeForce RTX 3080 · 10GB VRAM 335M F16 ✅ Runs comfortably 460–770 tok/s
AMD Radeon RX 6700 XT · 12GB VRAM 335M F16 ✅ Runs comfortably 220–370 tok/s
AMD Radeon RX 7700 XT · 12GB VRAM 335M F16 ✅ Runs comfortably 250–410 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM 335M F16 ✅ Runs comfortably 220–360 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM 335M F16 ✅ Runs comfortably 300–510 tok/s
AMD Radeon RX 6800 XT · 16GB VRAM 335M F16 ✅ Runs comfortably 290–490 tok/s

Already have a machine? See mxbai-embed-large 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 mxbai-embed-large --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.