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 Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  CodeLlama 34B Instruct Fp16   URL Share it on

  293   

CodeLlama 34B Instruct Fp16 is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 67.5GB, Context: 16K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.24, ELO: 1136, Arc: 40.8, HellaSwag: 35.7, MMLU: 39.7, GSM8K: 23.1.

  Codegen   Codellama   Custom code   Endpoints compatible   Fp16   Instruct   Llama   Llama2   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-34B-Instruct-fp16 

CodeLlama 34B Instruct Fp16 Benchmarks

LMSys ELO: 1136 vs 1272 (so35)-10.7%
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%
GSM8K: 23.05 vs 96.4 (so35)-76.1%
LLME Score: 0.23942
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 Fp16 (TheBloke/CodeLlama-34B-Instruct-fp16)
🌟 Advertise your project 🚀

CodeLlama 34B Instruct Fp16 Parameters and Internals

Model Type 
instruction following, code synthesis, text generation
Use Cases 
Areas:
Commercial, Research
Applications:
Code synthesis, Code understanding, Code assistive applications
Primary Use Cases:
Code assistant, Code generation
Limitations:
Use in languages other than English, Code use not covered by safety evaluations
Considerations:
Perform safety testing tailored to specific applications.
Additional Notes 
Model variants are designed for Python and safer deployment applications.
Supported Languages 
English (Full support), Python (Highly specialized support), Other programming languages (Partial support)
Training Details 
Methodology:
Fine-tuned with instruction data
Context Length:
100000
Hardware Used:
A100-80GB
Model Architecture:
Autoregressive, transformer architecture
LLM NameCodeLlama 34B Instruct Fp16
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-34B-Instruct-fp16 
Base Model(s)  CodeLlama 34B Instruct Hf   premai-io/CodeLlama-34b-Instruct-hf
Model Size34b
Required VRAM67.5 GB
Updated2026-05-05
MaintainerTheBloke
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
Quantization Typefp16
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to CodeLlama 34B Instruct Fp16

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 34B Instruct Hf 4bit16K / 19.4 GB692
...gpt 32K Codellama 34B Instruct32K / 67.5 GB8172
CodeLlama 34B Instruct Hf16K / 67.5 GB57493304
CodeLlama 34B Instruct Hf16K / 1.4 GB233
Speechless Codellama 34B V2.016K / 67.5 GB107317
CodeLlama 34B Instruct Hf16K / 67.5 GB155619
Speechless Codellama 34B V1.916K / 67.5 GB9080
CodeFuse CodeLlama 34B16K / 67.5 GB75493
XAgentLLaMa 34B Preview16K / 157.3 GB73
...chless Codellama 34B V2.0 GPTQ16K / 17.7 GB204
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-34B-Instruct-fp16.

Rank the CodeLlama 34B Instruct Fp16 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? 54415 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