Replit Code V1.5 3B by replit

 »  All LLMs  »  replit  »  Replit Code V1.5 3B   URL Share it on

Replit Code V1.5 3B is an open-source language model by replit. Features: 3b LLM, VRAM: 6.6GB, License: apache-2.0, LLM Explorer Score: 0.13.

  Code   Composer   Custom code Dataset:bigcode/the-stack-dedu... Dataset:togethercomputer/redpa...   Endpoints compatible   Llm-foundry   Mosaicml   Mpt   Pytorch   Region:us   Streamingdatasets

Replit Code V1.5 3B Benchmarks

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

Replit Code V1.5 3B Parameters and Internals

Model Type 
Causal Language Model
Use Cases 
Primary Use Cases:
Code completion
Limitations:
Pre-training dataset may have contained offensive or inappropriate content
Training Details 
Data Sources:
Bigcode's Stack Dedup dataset, RedPajama's StackExchange dataset
Data Volume:
1T tokens of code
Context Length:
4096
Hardware Used:
128 H100-80GB GPUs
Input Output 
Performance Tips:
Experiment with temperature and repetition_penalty for optimal performance
LLM NameReplit Code V1.5 3B
Repository 🤗https://huggingface.co/replit/replit-code-v1_5-3b 
Model Size3b
Required VRAM6.6 GB
Updated2026-05-03
Maintainerreplit
Model Typempt
Model Files  6.6 GB
Supported Languagescode
Model ArchitectureMPTForCausalLM
Licenseapache-2.0
Model Max Length4096
Transformers Version4.33.3
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Replit Code V1.5 3B

Best Alternatives
Context / RAM
Downloads
Likes
Replit Code V1 3B0K / 10.4 GB1131742
Sea Lion 3B0K / 6.4 GB77817
Code Millenials 3B0K / 5.2 GB181
SEA LION V1 3B0K / 6.4 GB15919
Mpt 3B 8K Instruct0K / 6.9 GB53
Glaive Function Calling V10K / 10.4 GB1775
...aive Function Calling V2 Small0K / 10.4 GB1515
Evol Replit V10K / 10.4 GB108
Replit V2 CodeInstruct 3B0K / 10.4 GB2571
Replit CodeInstruct V30K / 10.4 GB112

Rank the Replit Code V1.5 3B 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.

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