MegaMath Llama 3.2 3B by LLM360

 »  All LLMs  »  LLM360  »  MegaMath Llama 3.2 3B   URL Share it on

MegaMath Llama 3.2 3B is an open-source language model by LLM360. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: llama3.2.

  Arxiv:2504.02807   Code   Cot   Dataset:llm360/megamath   En   Endpoints compatible   Llama   Math   Pal   Region:us   Safetensors   Sharded   Tensorflow

MegaMath Llama 3.2 3B Parameters and Internals

LLM NameMegaMath Llama 3.2 3B
Repository 🤗https://huggingface.co/IFM/MegaMath-Llama-3.2-3B 
Model Size3b
Required VRAM6.5 GB
Updated2026-08-02
MaintainerLLM360
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.48.3
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to MegaMath Llama 3.2 3B

Best Alternatives
Context / RAM
Downloads
Likes
Nanbeige4.1 3B256K / 7.9 GB111381142
Nanbeige4.1 3B Heretic256K / 7.9 GB14950
Nanbeige4.1 3B Bf16256K / 7.9 GB473
Nanbeige4.1 3B Heretic Mxfp4256K / 7.9 GB342
Nanbeige4.1 3B Heretic256K / 7.9 GB41
Nanbeige4.1 3B Heretic256K / 7.9 GB70
ISA 03 Mini 3B Hybrid Preview256K / 6.5 GB44
Llama 3.2 3B Instruct128K / 6.5 GB18295722368
G9v3 3B128K / 6 GB21413
Llama 3.2 3B128K / 6.5 GB706937845
Note: green Score (e.g. "73.2") means that the model is better than IFM/MegaMath-Llama-3.2-3B.

Rank the MegaMath Llama 3.2 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? 55556 in total.

Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a