What are the hardware requirements for CodeLlama 70B Hf?

CodeLlama 70B Hf requires approximately 77 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeLlama 70B Hf and how large is it?

CodeLlama 70B Hf is developed by codellama, a model with 70b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeLlama 70B Hf perform on standard benchmarks?

CodeLlama 70B Hf has the following published scores: MMLU 59.67, HumanEval (Python) 52.44, LMSYS ELO 1056. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 70B Hf by codellama — VRAM 77GB, 16K context

Name: CodeLlama 70B Hf
Author: codellama

CodeLlama 70B Hf is an open-source language model by codellama. Features: 70b LLM, VRAM: 77GB, Context: 16K, License: llama2, Code Generating, LLM Explorer Score: 0.27, ELO: 1056, Arc: 56.7, HellaSwag: 78.2, MMLU: 59.7, GSM8K: 44, HumanEval: 52.4.

Arxiv:2308.12950 Code Codegen Deploy:azure Endpoints compatible Llama Llama2 Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/codellama/CodeLlama-70b-hf

CodeLlama 70B Hf Benchmarks

LMSys ELO: 1056 vs 1272 (so35)^-17%

ARC: 56.74 vs 96.7 (so35)^-41.3%

HellaSwag: 78.21 vs 95.3 (gpt4)^-17.9%

MMLU: 59.67 vs 88.3 (so35)^-32.4%

GSM8K: 43.97 vs 96.4 (so35)^-54.4%

HumanEvalA: 39.93

Python Eva: 52.44 vs 92 (so35)^-43%

Java Eval: 44.72

Javascript: 56.52

CPP Eval: 49.69

PHP Eval: 46.58

Julia Eval: 42.24

Swift Eval: 42.86

LLME Score: 0.26897

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

CodeLlama 70B Hf (codellama/CodeLlama-70b-hf)

🌟 Advertise your project 🚀

CodeLlama 70B Hf Parameters and Internals

Model Type

text generation

Use Cases

Areas:

commercial, research

Applications:

code synthesis, understanding tasks, Python programming, code assistant and generation

Limitations:

Use in languages other than English

Additional Notes

Code Llama is a non-official repository in Hugging Face format. Training involved 1400K GPU hours with offset emissions.

Supported Languages

English (high proficiency)

Training Details

Context Length:

16000

Model Architecture:

Auto-regressive language model using an optimized transformer architecture

Input Output

Input Format:

text only

Output Format:

text

LLM Name	CodeLlama 70B Hf
Repository 🤗	https://huggingface.co/codellama/CodeLlama-70b-hf
Model Size	70b
Required VRAM	77 GB
Updated	2026-05-16
Maintainer	codellama
Model Type	llama
Model Files	4.7 GB: 1-of-29 4.7 GB: 2-of-29 5.0 GB: 3-of-29 5.0 GB: 4-of-29 4.7 GB: 5-of-29 4.7 GB: 6-of-29 4.7 GB: 7-of-29 5.0 GB: 8-of-29 5.0 GB: 9-of-29 4.7 GB: 10-of-29 4.7 GB: 11-of-29 4.7 GB: 12-of-29 5.0 GB: 13-of-29 5.0 GB: 14-of-29 4.7 GB: 15-of-29 4.7 GB: 16-of-29 4.7 GB: 17-of-29 5.0 GB: 18-of-29 5.0 GB: 19-of-29 4.7 GB: 20-of-29 4.7 GB: 21-of-29 4.7 GB: 22-of-29 5.0 GB: 23-of-29 5.0 GB: 24-of-29 4.7 GB: 25-of-29 4.7 GB: 26-of-29 4.7 GB: 27-of-29 5.0 GB: 28-of-29 3.8 GB: 29-of-29 4.7 GB: 1-of-29 4.7 GB: 2-of-29 5.0 GB: 3-of-29 5.0 GB: 4-of-29 4.7 GB: 5-of-29 4.7 GB: 6-of-29 4.7 GB: 7-of-29 5.0 GB: 8-of-29 5.0 GB: 9-of-29 4.7 GB: 10-of-29 4.7 GB: 11-of-29 4.7 GB: 12-of-29 5.0 GB: 13-of-29 5.0 GB: 14-of-29 4.7 GB: 15-of-29 4.7 GB: 16-of-29
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.37.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32016
Torch Data Type	bfloat16

Quantized Models of the CodeLlama 70B Hf

Model	Likes	Downloads	VRAM
CodeLlama 70B Hf GGUF	42	495	25 GB
CodeLlama 70B Hf GPTQ	10	13	35 GB
CodeLLaMA 70B Hf Fp16	2	58	138 GB
CodeLlama 70B Hf AWQ	4	13	36 GB

Best Alternatives to CodeLlama 70B Hf

Best Alternatives	Context / RAM	Downloads	Likes
Sqlcoder 70B Alpha	16K / 138.7 GB	56	232
CodeLlama 70B Hf	16K / 77 GB	15	27
BigCodeLlama 169B	16K / 338.2 GB	550	14
...enbuddy Codellama 70B V17.1 4K	16K / 138.9 GB	7	1
...enbuddy Codellama 70B V17.1 4K	16K / 138.9 GB	5	1
CodeLlama 70B Instruct Hf	4K / 72.3 GB	799	24
Code Llama 70B Python Instruct	4K / 138.1 GB	5	1
CodeLlama 70B Instruct Hf	4K / 72.3 GB	1306	208
CodeLlama 70B Python Hf	4K / 77 GB	1027	111
CodeRosa 70B AB1	4K / 61.3 GB	119	1

Rank the CodeLlama 70B Hf Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

CodeLlama 70B Hf by codellama