fishaudio models

2 fishaudio models from fishaudio on Hugging Face, from 4.6B to 35.9B parameters, published by fishaudio in BF16 and F8_E4M3, with a 256K-token context. The smallest official model, s2-pro, needs about 10.2 GB of VRAM at its published precision; the cheapest live fit is RTX 3060 at $0.110/hr.

Pick a size

One row per official fishaudio 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
s2-pro4.6B10.2 GB5.1 GB2.5 GBRTX 3060$0.110/hr18.0 GB
drama-335.9B40.1 GB–20.1 GBL40$0.759/hrnot published for this architecture

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 (2)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
s2-pro4.6BBF1610.2 GBRTX 3060$0.110/hr
drama-335.9BF8_E4M340.1 GBL40$0.759/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.