meta-models models

1 meta-models model from meta-models on Hugging Face, from 29.8B to 29.8B parameters, published by meta-models in BF16, with a 128K-token context. The smallest official model, Muse-Glimmer-30B, needs about 66.6 GB of VRAM at its published precision; the cheapest live fit is A100 at $1.31/hr.

Pick a size

One row per official meta-models 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
Muse-Glimmer-30B29.8B66.6 GB33.3 GB16.6 GBA100$1.31/hr0.48 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 (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Muse-Glimmer-30B29.8BBF1666.6 GBA100$1.31/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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