LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

CodeLlama 34B Instruct Hf by meta-llama

 »  All LLMs  »  meta-llama  »  CodeLlama 34B Instruct Hf   URL Share it on

  821   

CodeLlama 34B Instruct Hf is an open-source language model by meta-llama. Features: 34b LLM, VRAM: 67.5GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.13.

  Arxiv:2308.12950   Code   Codegen   Conversational   Endpoints compatible   Facebook   Instruct   Llama   Llama2   Meta   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/meta-llama/CodeLlama-34b-Instruct-hf 

CodeLlama 34B Instruct Hf Benchmarks

LLME Score: 0.13397
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 34B Instruct Hf (meta-llama/CodeLlama-34b-Instruct-hf)
🌟 Advertise your project 🚀

CodeLlama 34B Instruct Hf Parameters and Internals

Model Type 
generative, text generation
Use Cases 
Areas:
commercial, research
Applications:
general code synthesis, understanding tasks
Primary Use Cases:
code assistant and generation
Limitations:
Potential for inaccurate or objectionable responses, Testing conducted in English only
Considerations:
Developers should perform safety testing before deployment.
Additional Notes 
All 9 Code Llama models required 400K GPU hours with emissions offset by Meta’s sustainability program.
Training Details 
Data Sources:
Same data as Llama 2 with different weights
Hardware Used:
Meta’s Research Super Cluster, Hardware of type A100-80GB (TDP of 350-400W)
Model Architecture:
Optimized transformer architecture
Responsible Ai Considerations 
Fairness:
Conduct safety testing and tuning tailored to specific applications.
Accountability:
Developers should ensure safe application deployment.
Mitigation Strategies:
Responsible Use Guide is available at Meta's website.
Input Output 
Input Format:
text only
Output Format:
text only
LLM NameCodeLlama 34B Instruct Hf
Repository 🤗https://huggingface.co/meta-llama/CodeLlama-34b-Instruct-hf 
Model Size34b
Required VRAM67.5 GB
Updated2026-04-11
Maintainermeta-llama
Model Typellama
Instruction-BasedYes
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 Languagescode
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.0.dev0
Tokenizer ClassCodeLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to CodeLlama 34B Instruct Hf

Best Alternatives
Context / RAM
Downloads
Likes
...gpt 32K Codellama 34B Instruct32K / 67.5 GB5022
CodeLlama 34B Instruct Hf16K / 67.5 GB21226304
CodeLlama 34B Instruct Hf16K / 1.4 GB63
Speechless Codellama 34B V2.016K / 67.5 GB101917
Speechless Codellama 34B V1.916K / 67.5 GB10180
CodeFuse CodeLlama 34B16K / 67.5 GB198293
XAgentLLaMa 34B Preview16K / 157.3 GB153
...gpt 16K Codellama 34B Instruct16K / 67.5 GB6214
MathCoder CL 34B16K / 67.5 GB113
CodeLlama 34B Instruct Hf16K / 1.4 GB53
Note: green Score (e.g. "73.2") means that the model is better than meta-llama/CodeLlama-34b-Instruct-hf.

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