ModelRein
Home / Answers / Supported models and hardware

Which open-source models ModelRein supports and how big a GPU you need (6 adapters, 40+ models)

ModelRein (formerly LMCP) is an HTTP protocol and reference server for controlling open-source foundation models: 27 primitives and 6 architecture adapters. Today it is used from the Rescot desktop app, which connects to your own GPU server over SSH (v0.4).

Which open-source models does ModelRein support?

ModelRein covers 40+ open-source models via 6 adapters: causal LMs, UNet and DiT image diffusion, vision-language, audio diffusion and video DiT (2026-10-09).

FactValueTypeAs ofSource
Architecture adapters6: causal_lm, unet, dit, vlm, audio_diffusion, video_ditSite docs2026-10-09about.html
Open-source models adapted40+Site docs2026-10-09models.html
Limits

How big a GPU do I need to run ModelRein?

ModelRein has no hardware floor; the model sets it: 0.5B runs on CPU, 1.5B fits about 6 GB VRAM, 70B needs 1–2 H100s; no CUDA means CPU (2026-10-09).

FactValueTypeAs ofSource
Hardware scales with the model0.5B runs on CPU; 1.5B fits about 6 GB VRAM; 70B needs 1–2 H100s; falls back to CPU without CUDASite docs2026-10-09lmcp-quickstart.html
RequirementsPython 3.10+; Linux / macOS 13+ / Windows 11; GPU optional; at least 8 GB RAMSite docs2026-10-09lmcp-quickstart.html
Limits

Related questions

What is ModelRein · Model control protocol vs tool-calling protocol · Connect Rescot to a GPU server to use ModelRein · Supported models and hardware

Every number carries an as-of date and a source. Data built 2026-11-04 · Rescot desktop app · llms.txt · sitemap