Llama 3 models

19 Llama 3 models from Meta on Hugging Face, from 8.0B to 70.6B parameters, published by Meta in BF16, with a 8K-token context. The smallest official model, Meta-Llama-3-8B, needs about 17.9 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.

Part of the Llama series · Previous generation: Llama 2 · Next generation: Llama 3.1

Pick a size

One row per official Llama 3 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
Meta-Llama-3-8B-Instruct8.0B17.9 GB9.0 GB4.5 GBRTX A5000$0.176/hr4.0 GB
Meta-Llama-3-70B70.6B158 GB78.8 GB39.4 GBAMD MI300X$2.63/hr10.0 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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Meta-Llama-3-8B8.0BBF1617.9 GBRTX A5000$0.176/hr
Meta-Llama-3-8B-Instruct8.0BBF1617.9 GBRTX A5000$0.176/hr
Meta-Llama-3-70B70.6BBF16158 GBAMD MI300X$2.63/hr
Meta-Llama-3-70B-Instruct70.6BBF16158 GBAMD MI300X$2.63/hr

Fine-tunes and community models (15)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Bio-Medical-Llama-3-8B8.0BBF1617.9 GBRTX A5000$0.176/hr
Llama-3-8b-Ita8.0BBF1617.9 GBRTX A5000$0.176/hr
Llama3-Chinese-8B-Instruct8.0BF1617.9 GBRTX A5000$0.176/hr
Llama-3-8B-Instruct-Gradient-1048k8.0BBF1617.9 GBRTX A5000$0.176/hr
finance-Llama3-8B8.0BF3235.9 GBRTX A6000$0.363/hr
Tess-2.0-Llama-3-8B8.0BF1617.9 GBRTX A5000$0.176/hr
NeuralDaredevil-8B-abliterated8.0BF1617.9 GBRTX A5000$0.176/hr
openchat-3.6-8b-202405228.0BBF1617.9 GBRTX A5000$0.176/hr
Llama-3-Patronus-Lynx-8B-Instruct-v1.18.0BF1617.9 GBRTX A5000$0.176/hr
Llama-3-8B-ProLong-64k-Base8.0BF3235.9 GBRTX A6000$0.363/hr
Llama-3-8B-UltraMedical8.0BBF1617.9 GBRTX A5000$0.176/hr
llama-3-8b8.0BBF1617.9 GBRTX A5000$0.176/hr
llama-3-8b-Instruct8.0BBF1617.9 GBRTX A5000$0.176/hr
Llama3-ChatQA-1.5-8B8.0BF1617.9 GBRTX A5000$0.176/hr
Llama-3-Taiwan-8B-Instruct8.0BBF1617.9 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 Llama 3

More from Meta

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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