Trinity models

3 Trinity models from arcee-ai on Hugging Face, from 6.1B to 398.6B parameters, published by arcee-ai in BF16, with contexts from 128K to 256K tokens. The smallest official model, Trinity-Nano-Preview, needs about 13.7 GB of VRAM at its published precision; the cheapest live fit is RTX A4000 at $0.167/hr.

Pick a size

One row per official Trinity size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Trinity-Nano-Preview6.1B13.7 GB6.8 GB3.4 GBRTX A4000$0.167/hr0.52 GB
Trinity-Mini26.1B58.4 GB29.2 GB14.6 GBA100$1.31/hr0.59 GB
Trinity-Large-Preview398.6B891 GB446 GB223 GBAMD MI300X × 5$13.14/hr2.6 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (3)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Trinity-Nano-Preview6.1BBF1613.7 GBRTX A4000$0.167/hr
Trinity-Mini26.1BBF1658.4 GBA100$1.31/hr
Trinity-Large-Preview398.6BBF16891 GBAMD MI300X × 5$13.14/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from arcee-ai

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.