Typhoon models

6 Typhoon models from typhoon-ai on Hugging Face, from 2.1B to 30.5B parameters, published by typhoon-ai in BF16, with contexts from 8K to 256K tokens. The smallest official model, typhoon-ocr1.5-2b, needs about 4.8 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official Typhoon 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
typhoon-ocr1.5-2b2.1B4.8 GB2.4 GB1.2 GBRTX 3070$0.088/hr3.5 GB
typhoon-ocr-3b3.8B8.4 GB4.2 GB2.1 GBRTX 3060$0.110/hr1.1 GB
typhoon2.5-qwen3-4b4.0B9.0 GB4.5 GB2.2 GBRTX 3060$0.110/hr4.5 GB
llama3.1-typhoon2-8b-instruct8.0B17.9 GB9.0 GB4.5 GBRTX A5000$0.176/hr4.0 GB
typhoon2.5-qwen3-30b-a3b30.5B68.2 GB34.1 GB17.1 GBA100$1.18/hr3.0 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 (6)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
typhoon-ocr1.5-2b2.1BBF164.8 GBRTX 3070$0.088/hr
typhoon-ocr-3b3.8BBF168.4 GBRTX 3060$0.110/hr
typhoon2.5-qwen3-4b4.0BBF169.0 GBRTX 3060$0.110/hr
llama-3-typhoon-v1.5-8b-instruct8.0BBF1617.9 GBRTX A5000$0.176/hr
llama3.1-typhoon2-8b-instruct8.0BBF1617.9 GBRTX A5000$0.176/hr
typhoon2.5-qwen3-30b-a3b30.5BBF1668.2 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.