Phi Mini MoE 7.6B locally
Phi Mini MoE 7.6B is an open-weight LLM from the Phi family with 7.6B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: GTX 1060 6GB (6 GB).
Available quantizations
GGUF weightsAcceptable. Good compromise when VRAM is limited.
Good quality. Sweet spot for size and precision.
Near-FP16 quality. Comfortable for production.
Reference precision. Maximum quality, doubled VRAM.
Compatible GPUs
12 single-GPUGPUs that can run Phi Mini MoE 7.6B on a single card, ranked by VRAM headroom.
Recommended multi-GPU rigs
2x / 4x consumer GPUsFor Phi Mini MoE 7.6B at higher quantization or with more context, a multi-GPU rig gives more headroom.
Recommended rig
Phi Mini MoE 7.6B with Ubuntu, vLLM, Open WebUI and the model already downloaded.
Similar models
VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12