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

Cotype Nano by MTSAIR

 »  All LLMs  »  MTSAIR  »  Cotype Nano   URL Share it on

  668   

Cotype Nano is an open-source language model by MTSAIR. Features: 1.5b LLM, VRAM: 3.1GB, Context: 32K, License: other, LLM Explorer Score: 0.22.

  Conversational   Deploy:azure   En   Endpoints compatible   Qwen2   Region:us   Ru   Safetensors
Model Card on HF 🤗: https://huggingface.co/MTSAIR/Cotype-Nano 

Cotype Nano Benchmarks

MMLU Pro: 16.41
GPQA: 2.68
MUSR: 2.11
BBH: 14.45
IFEval: 37.48 vs 88 (so35)-57.4%
MATH Lvl 5: 9.74
LLME Score: 0.22453
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cotype Nano (MTSAIR/Cotype-Nano)
🌟 Advertise your project 🚀

Cotype Nano Parameters and Internals

Model Type 
text-generation
Additional Notes 
Cotype-Nano is optimized for fast and efficient interaction with users, providing high performance even under resource-constrained conditions.
Supported Languages 
ru (unknown), en (unknown)
Training Details 
Data Sources:
internal and open synthetic instructional datasets
Methodology:
The model was trained in two stages. In the first stage, MLP layers were trained on mathematics and code. In the second stage, the entire model was trained
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
LLM NameCotype Nano
Repository 🤗https://huggingface.co/MTSAIR/Cotype-Nano 
Model Size1.5b
Required VRAM3.1 GB
Updated2026-03-29
MaintainerMTSAIR
Model Typeqwen2
Model Files  3.1 GB
Supported Languagesru en
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Cotype Nano

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.1 GB18207775
Reader Lm 1.5B250K / 3.1 GB456608
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB8307481465
VibeThinker 1.5B128K / 3.5 GB1432516
Ko R1 1.5B Preview128K / 7.1 GB659
Qwen2.5 1.5B128K / 3.1 GB888741150
AceInstruct 1.5B128K / 3.5 GB7688020
DeepScaleR 1.5B Preview128K / 7.1 GB11774573
Qwen2 1.5B128K / 3.1 GB146613101
...n Research Reasoning Qwen 1.5B128K / 7.1 GB5716221
Note: green Score (e.g. "73.2") means that the model is better than MTSAIR/Cotype-Nano.

Rank the Cotype Nano 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