Ornith 1 models

17 Ornith 1 models from ornith-ai on Hugging Face, from 4.3B to 403.4B parameters, published by ornith-ai in BF16, with a 256K-token context. The smallest official model, Ornith-1.5-9B, needs about 21.6 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.

Pick a size

One row per official Ornith 1 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
Ornith-1.5-9B9.7B21.6 GB10.8 GB5.4 GBRTX A5000$0.176/hr1.0 GB
Ornith-1.5-35B-A3B36.0B80.4 GB40.2 GB20.1 GBRTX PRO 6000$1.38/hr0.63 GB
Ornith-1.0-397B396.8B887 GB443 GB222 GBAMD MI300X × 5$13.14/hr0.94 GB
Ornith-1.5-397B403.4B902 GB451 GB225 GBAMD MI300X × 5$13.14/hr0.94 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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Ornith-1.5-9B9.7BBF1621.6 GBRTX A5000$0.176/hr
Ornith-1.5-35B-A3B36.0BBF1680.4 GBRTX PRO 6000$1.38/hr
Ornith-1.0-397B396.8BBF16887 GBAMD MI300X × 5$13.14/hr
Ornith-1.5-397B403.4BBF16902 GBAMD MI300X × 5$13.14/hr

Quantized versions (11)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Ornith-1.5-9B-INT4-W4A16-AutoRound4.3BBF169.7 GBRTX 3060$0.110/hr
Ornith-1.5-9B-MLX9.0BBF1620.0 GBRTX A5000$0.176/hr
Ornith-1.5-35B-A3B-MLX34.7BBF1677.5 GBA100$1.18/hr
Ornith-1.0-35B-FP835.1BF8_E4M339.2 GBL40$0.759/hr
Ornith-1.0-35B-FP835.1BF8_E4M339.2 GBL40$0.759/hr
Ornith-1.0-35B-AWQ-FP835.1BF8_E4M339.3 GBL40$0.759/hr
Ornith-1.0-35B-FP835.1BF8_E4M339.3 GBL40$0.759/hr
Ornith-1.5-35B-A3B-FP836.0BF8_E4M340.2 GBL40$0.759/hr
Ornith-1.0-397B-FP8396.8BF8_E4M3443 GBRTX PRO 6000 × 5$6.88/hr
Ornith-1.0-397B-FP8397.0BF8_E4M3444 GBRTX PRO 6000 × 5$6.88/hr
Ornith-1.5-397B-FP8403.4BF8_E4M3451 GBRTX PRO 6000 × 5$6.88/hr

Fine-tunes and community models (2)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Ornith-1.5-9B-OBLITERATED9.7BBF1621.6 GBRTX A5000$0.176/hr
Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF1635.1BBF1678.5 GBA100$1.18/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.