Code Llama models

3 Code Llama models from Meta on Hugging Face, from 6.7B to 33.7B parameters, published by Meta in BF16, with a 16K-token context. The smallest official model, CodeLlama-7b-hf, needs about 15.1 GB of VRAM at its published precision; the cheapest live fit is RTX A4000 at $0.173/hr.

Part of the Llama series

Pick a size

One row per official Code Llama 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
CodeLlama-7b-hf6.7B15.1 GB7.5 GB3.8 GBRTX A4000$0.173/hr16.0 GB
CodeLlama-34b-Instruct-hf33.7B75.4 GB37.7 GB18.9 GBA100$1.18/hr6.0 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 (3)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
CodeLlama-7b-hf6.7BBF1615.1 GBRTX A4000$0.173/hr
CodeLlama-7b-Instruct-hf6.7BBF1615.1 GBRTX A4000$0.173/hr
CodeLlama-34b-Instruct-hf33.7BBF1675.4 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.

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.