AxForge
Sign in Get started

Model reference · open weights

CodeLlama

LLMs meta-llama Text gen 1 build Open, with conditions 3k dl/mo

CodeLlama is an open-weight language model from Meta. CodeLlama-7b-Instruct-hf (BF16) weighs 13.5 GB; the smallest configuration that runs it is RTX 4060 Ti 16 GB.

  • CodeLlama is a 6.7 billion parameter generative text model developed by Meta for code synthesis and understanding.
  • It is an auto-regressive transformer designed for general code tasks, including completion and infilling, and is intended for use in English and relevant programming languages.
  • The model is distributed under the llama2 license.

Summary of the meta-llama/CodeLlama-7b-Instruct-hf model card, 2026-10-01

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released byMeta
Released2024-03-13
Parameters6.7B
VRAM13.5 GB for the weights

What it runs on

Memory and cards for CodeLlama-7b-Instruct-hf (BF16)

13.5 GBweights, file size
762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GBdoes not fit
RTX 4060 Ti 16 GBtight
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms