Falcon3 models

4 Falcon3 models from TII on Hugging Face, from 1.7B to 7.5B parameters, published by TII in BF16, with contexts from 4K to 32K tokens. The smallest official model, Falcon3-1B-Base, needs about 3.7 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Part of the Falcon series · Previous generation: Falcon 1

Pick a size

One row per official Falcon3 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
Falcon3-1B-Instruct1.7B3.7 GB1.9 GB0.9 GBRTX 3070$0.088/hr2.3 GB
Falcon3-7B-Instruct7.5B16.7 GB8.3 GB4.2 GBRTX A5000$0.176/hr3.5 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
Falcon3-1B-Base1.7BBF163.7 GBRTX 3070$0.088/hr
Falcon3-1B-Instruct1.7BBF163.7 GBRTX 3070$0.088/hr
Falcon3-7B-Base7.5BBF1616.7 GBRTX A5000$0.176/hr
Falcon3-7B-Instruct7.5BBF1616.7 GBRTX A5000$0.176/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.

Run and fine-tune Falcon3

More from TII

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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