What are the hardware requirements for CodeLlama 70B Instruct Hf?

CodeLlama 70B Instruct Hf requires approximately 72.3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

CodeLlama 70B Instruct 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 Instruct Hf perform on standard benchmarks?

CodeLlama 70B Instruct Hf has the following published scores: MMLU 56.4, HumanEval (Python) 75.6. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 70B Instruct Hf by codellama — VRAM 72.3GB, 4K context

Name: CodeLlama 70B Instruct Hf
Author: codellama

CodeLlama 70B Instruct Hf is an open-source language model by codellama. Features: 70b LLM, VRAM: 72.3GB, Context: 4K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.16, Arc: 55, HellaSwag: 77.2, MMLU: 56.4, GSM8K: 46.3, HumanEval: 75.6.

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

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

CodeLlama 70B Instruct Hf Benchmarks

ARC: 55.03 vs 96.7 (so35)^-43.1%

HellaSwag: 77.24 vs 95.3 (gpt4)^-19%

MMLU: 56.4 vs 88.3 (so35)^-36.1%

GSM8K: 46.25 vs 96.4 (so35)^-52%

HumanEvalA: 42.64

Python Eva: 75.6 vs 92 (so35)^-17.8%

Java Eval: 47.2

Javascript: 57.76

CPP Eval: 48.45

PHP Eval: 57.14

Julia Eval: 42.24

Swift Eval: 42.86

LLME Score: 0.15778

^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 Instruct Hf (codellama/CodeLlama-70b-Instruct-hf)

🌟 Advertise your project 🚀

CodeLlama 70B Instruct Hf Parameters and Internals

Model Type

text-generation, code synthesis

Use Cases

Areas:

Commercial use, Research

Primary Use Cases:

Code synthesis and understanding, Python programming, Instruction following

Considerations:

Use in English and relevant programming languages.

Supported Languages

English (General proficiency, focused on code synthesis and understanding)

Training Details

Context Length:

16000

Hardware Used:

Meta’s Research Super Cluster, A100-80GB GPUs

Model Architecture:

Auto-regressive language model with an optimized transformer architecture.

Input Output

Input Format:

Text only

Output Format:

Text only

LLM Name	CodeLlama 70B Instruct Hf
Repository 🤗	https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf
Model Size	70b
Required VRAM	72.3 GB
Updated	2026-05-05
Maintainer	codellama
Model Type	llama
Instruction-Based	Yes
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
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.1
Vocabulary Size	32016
Torch Data Type	bfloat16

Quantized Models of the CodeLlama 70B Instruct Hf

Model	Likes	Downloads	VRAM
CodeLlama 70B Instruct GGUF	63	1490	25 GB
CodeLlama 70B Instruct GPTQ	15	156	35 GB
CodeLlama 70B Instruct Hf GGUF	2	121	25 GB
CodeLlama 70B Instruct AWQ	13	51	36 GB

Best Alternatives to CodeLlama 70B Instruct Hf

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 70B Instruct Hf	4K / 72.3 GB	799	24
Code Llama 70B Python Instruct	4K / 138.1 GB	5	1
CodeLlama 70B Instruct Neuron	4K / GB	11	1
BigCodeLlama 92B	2K / 184 GB	119	0
...Llama 70B Instruct Hf 4bit MLX	4K / 39.1 GB	664	25
...70B Instruct Nf4 Fp16 Upscaled	4K / 138.7 GB	10	2
...70B Instruct Hf 5.0bpw H6 EXL2	2K / 43.6 GB	6	6
...70B Instruct Hf 2.4bpw H6 EXL2	2K / 21.3 GB	3	1
...0B Instruct Hf 2.65bpw H6 EXL2	2K / 23.4 GB	5	3
...70B Instruct Hf 4.0bpw H6 EXL2	2K / 35.1 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than codellama/CodeLlama-70b-Instruct-hf.

Rank the CodeLlama 70B Instruct 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 Instruct Hf by codellama