Nanbeige models

4 Nanbeige models from Nanbeige on Hugging Face, from 848M to 33.1B parameters, published by Nanbeige in BF16, with contexts from 256K to 512K tokens. The smallest official model, Nanbeige4.2-3B-DSpark, needs about 1.9 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 Nanbeige 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
Nanbeige4.2-3B-DSpark848M1.9 GB0.9 GB0.5 GBRTX 3070$0.088/hr0.63 GB
Nanbeige4.1-3B3.9B8.8 GB4.4 GB2.2 GBRTX A4000$0.173/hr2.0 GB
Nanbeige4.2-3B4.2B9.3 GB4.7 GB2.3 GBRTX A4000$0.173/hr2.8 GB
Nanbeige4.3-33B33.1B74.0 GB37.0 GB18.5 GBA100$1.31/hr6.5 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
Nanbeige4.2-3B-DSpark848MBF161.9 GBRTX 3070$0.088/hr
Nanbeige4.1-3B3.9BBF168.8 GBRTX A4000$0.173/hr
Nanbeige4.2-3B4.2BBF169.3 GBRTX A4000$0.173/hr
Nanbeige4.3-33B33.1BBF1674.0 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.