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

NanoLM 0.3B Instruct V1 by Mxode

 »  All LLMs  »  Mxode  »  NanoLM 0.3B Instruct V1   URL Share it on

  18   

NanoLM 0.3B Instruct V1 is an open-source language model by Mxode. Features: 0.3b LLM, VRAM: 0.6GB, Context: 128K, License: gpl-3.0, Instruction-Based, LLM Explorer Score: 0.17.

  Conversational   En   Instruct   Model-index   Qwen2   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/Mxode/NanoLM-0.3B-Instruct-v1 

NanoLM 0.3B Instruct V1 Benchmarks

MMLU Pro: 1.17
GPQA: 2.91
MUSR: 10.44
BBH: 3.1
IFEval: 15.37 vs 88 (so35)-82.5%
MATH Lvl 5: 1.44
LLME Score: 0.16783
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NanoLM 0.3B Instruct V1 (Mxode/NanoLM-0.3B-Instruct-v1)
🌟 Advertise your project 🚀

NanoLM 0.3B Instruct V1 Parameters and Internals

Model Type 
text2text-generation, text-generation
Additional Notes 
The model is part of the NanoLM Collections aimed at exploring the potential of small models.
Supported Languages 
en (Fluent), zh (Fluent)
Training Details 
Methodology:
Reduced number of layers from 24 to 12
Model Architecture:
Same as Qwen/Qwen2-0.5B but reduced layers to 12
Input Output 
Accepted Modalities:
text
Performance Tips:
Configure sampling parameters appropriately for better response quality.
LLM NameNanoLM 0.3B Instruct V1
Repository 🤗https://huggingface.co/Mxode/NanoLM-0.3B-Instruct-v1 
Model Size0.3b
Required VRAM0.6 GB
Updated2025-12-13
MaintainerMxode
Model Typeqwen2
Instruction-BasedYes
Model Files  0.6 GB
Supported Languagesen zh
Model ArchitectureQwen2ForCausalLM
Licensegpl-3.0
Context Length131072
Model Max Length131072
Transformers Version4.42.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to NanoLM 0.3B Instruct V1

Best Alternatives
Context / RAM
Downloads
Likes
NanoLM 0.3B Instruct V1.1128K / 0.6 GB72
NanoLM 0.3B Instruct V2128K / 0.6 GB130
Note: green Score (e.g. "73.2") means that the model is better than Mxode/NanoLM-0.3B-Instruct-v1.

Rank the NanoLM 0.3B Instruct V1 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? 52721 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