What are the hardware requirements for CodeLlama 34B Instruct Hf?

CodeLlama 34B Instruct Hf requires approximately 67.5 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 34B Instruct Hf and how large is it?

CodeLlama 34B Instruct Hf is developed by codellama, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeLlama 34B Instruct Hf perform on standard benchmarks?

CodeLlama 34B Instruct Hf has the following published scores: MMLU 39.72, HumanEval (Python) 50.79, LMSYS ELO 1058. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 34B Instruct Hf by codellama — VRAM 67.5GB, 16K context

Name: CodeLlama 34B Instruct Hf
Author: codellama

CodeLlama 34B Instruct Hf is an open-source language model by codellama. Features: 34b LLM, VRAM: 67.5GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, HF Score: 44.3, LLM Explorer Score: 0.29, ELO: 1058, Arc: 40.8, HellaSwag: 35.7, MMLU: 39.7, TruthfulQA: 44.3, WinoGrande: 74.5, GSM8K: 31, HumanEval: 50.8.

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

Model Card on HF 🤗: https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf

CodeLlama 34B Instruct Hf Benchmarks

LMSys ELO: 1058 vs 1272 (so35)^-16.8%

ARC: 40.78 vs 96.7 (so35)^-57.8%

HellaSwag: 35.66 vs 95.3 (gpt4)^-62.6%

MMLU: 39.72 vs 88.3 (so35)^-55%

TruthfulQA: 44.29 vs 59 (gpt4)^-24.9%

WinoGrande: 74.51 vs 87.5 (gpt4)^-14.8%

GSM8K: 31.01 vs 96.4 (so35)^-67.8%

HumanEvalA: 35.09

Python Eva: 50.79 vs 92 (so35)^-44.8%

Java Eval: 41.53

Javascript: 45.85

CPP Eval: 41.53

PHP Eval: 36.98

Julia Eval: 32.65

D Eval: 13.63

Lua Eval: 38.87

R Eval: 24.25

Racket Eva: 18.09

Rust Eval: 39.26

Swift Eval: 37.63

LLME Score: 0.285

^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 34B Instruct Hf (codellama/CodeLlama-34b-Instruct-hf)

🌟 Advertise your project 🚀

CodeLlama 34B Instruct Hf Parameters and Internals

Model Type

text generation, code synthesis, instruction following

Use Cases

Areas:

Commercial use, Research

Applications:

Code synthesis, Understanding tasks

Primary Use Cases:

Code assistant, Code generation

Limitations:

Use only in English, Potential production of inaccurate or objectionable responses

Supported Languages

Programming Languages (Python), Human Languages (English)

Training Details

Methodology:

Uses an optimized transformer architecture. Trained on similar data as Llama 2.

Training Time:

January 2023 - July 2023

Hardware Used:

A100-80GB GPUs

Model Architecture:

Auto-regressive language model

Safety Evaluation

Methodologies:

Safety evaluations include tests in English.

Ethical Considerations:

Use in languages other than English may produce unpredictable results.

Responsible Ai Considerations

Accountability:

Developers should perform safety testing tailored to specific applications.

Mitigation Strategies:

Detailed in Responsible Use Guide.

Input Output

Input Format:

Text input only

Accepted Modalities:

text

Output Format:

Generates text only

Performance Tips:

Ensure proper safety testing and tuning before deploying applications.

LLM Name	CodeLlama 34B Instruct Hf
Repository 🤗	https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
Model Size	34b
Required VRAM	67.5 GB
Updated	2026-04-11
Maintainer	codellama
Model Type	llama
Instruction-Based	Yes
Model Files	9.8 GB: 1-of-7 9.7 GB: 2-of-7 9.7 GB: 3-of-7 9.7 GB: 4-of-7 9.7 GB: 5-of-7 9.7 GB: 6-of-7 9.2 GB: 7-of-7 9.8 GB: 1-of-7 9.7 GB: 2-of-7 9.7 GB: 3-of-7 9.7 GB: 4-of-7 9.7 GB: 5-of-7 9.7 GB: 6-of-7 9.4 GB: 7-of-7
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0.dev0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the CodeLlama 34B Instruct Hf

Model	Likes	Downloads	VRAM
CodeLlama 34B Instruct Hf GGUF	1	598	12 GB

Best Alternatives to CodeLlama 34B Instruct Hf

Best Alternatives	Context / RAM	Downloads	Likes
...gpt 32K Codellama 34B Instruct	32K / 67.5 GB	502	2
CodeLlama 34B Instruct Hf	16K / 1.4 GB	6	3
Speechless Codellama 34B V2.0	16K / 67.5 GB	1019	17
CodeLlama 34B Instruct Hf	16K / 67.5 GB	821	19
Speechless Codellama 34B V1.9	16K / 67.5 GB	1018	0
CodeFuse CodeLlama 34B	16K / 67.5 GB	1982	93
XAgentLLaMa 34B Preview	16K / 157.3 GB	15	3
...gpt 16K Codellama 34B Instruct	16K / 67.5 GB	621	4
MathCoder CL 34B	16K / 67.5 GB	11	3
CodeLlama 34B Instruct Hf	16K / 1.4 GB	5	3

Rank the CodeLlama 34B 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? 53232 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 34B Instruct Hf by codellama