LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

OncoReasoning 3B 0825 by ksg-dfci

 »  All LLMs  »  ksg-dfci  »  OncoReasoning 3B 0825   URL Share it on

  35   
  Autotrain compatible   Clinical-trials   Conversational   Distillation   En   Endpoints compatible   Information-extraction   Llama   Llama-3.2   Oncology   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ksg-dfci/OncoReasoning-3B-0825 

OncoReasoning 3B 0825 Benchmarks

LLME Score: 0.27498
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OncoReasoning 3B 0825 (ksg-dfci/OncoReasoning-3B-0825)
🌟 Advertise your project 🚀

OncoReasoning 3B 0825 Parameters and Internals

LLM NameOncoReasoning 3B 0825
Repository 🤗https://huggingface.co/ksg-dfci/OncoReasoning-3B-0825 
Model Size3b
Required VRAM6.5 GB
Updated2025-09-16
Maintainerksg-dfci
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 Version4.55.4
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to OncoReasoning 3B 0825

Best Alternatives
Context / RAM
Downloads
Likes
ISA 03 Mini 3B Hybrid Preview256K / 6.5 GB10684
Llama 3.2 3B Instruct128K / 6.5 GB18386811704
Llama 3.2 3B128K / 6.5 GB643340629
DeepSeek R1 Distill Llama 3B128K / 6.5 GB133416
Hermes 3 Llama 3.2 3B128K / 6.5 GB7451171
Discord Micae Hermes 3 3B128K / 6.5 GB11668
FuseChat Llama 3.2 3B Instruct128K / 6.5 GB12317
Orpheus 3B 0.1 Ft128K / 6.6 GB348008
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB72
Calme 3.1 Llamaloi 3B128K / 10.6 GB22931
Note: green Score (e.g. "73.2") means that the model is better than ksg-dfci/OncoReasoning-3B-0825.

Rank the OncoReasoning 3B 0825 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? 51408 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.
Release v20241124
  Support LLM Explorer