Medalpaca Lora 30B 8bit by medalpaca

 »  All LLMs  »  medalpaca  »  Medalpaca Lora 30B 8bit   URL Share it on

Medalpaca Lora 30B 8bit is an open-source language model by medalpaca. Features: 30b LLM, VRAM: 0.2GB, License: cc, Quantized, LLM Explorer Score: 0.06.

  Arxiv:2106.09685   Arxiv:2303.14070   8bit   En   Endpoints compatible   Lora   Medical   Quantized   Region:us

Medalpaca Lora 30B 8bit Benchmarks

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

Medalpaca Lora 30B 8bit Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
medical domain tasks
Primary Use Cases:
question-answering, medical dialogue tasks
Limitations:
May not perform effectively outside medical domain, Primarily targets medical students' knowledge level, Not tested in real-world applications
Considerations:
It should not substitute a doctor's opinion.
Supported Languages 
en (English)
Training Details 
Data Sources:
Anki flashcards, Wikidoc, StackExchange, ChatDoctor dataset
Methodology:
LoRA fine-tuning and quantization
Model Architecture:
Based on LLaMA
LLM NameMedalpaca Lora 30B 8bit
Repository 🤗https://huggingface.co/medalpaca/medalpaca-lora-30b-8bit 
Model Size30b
Required VRAM0.2 GB
Updated2026-06-23
Maintainermedalpaca
Model Files  0.2 GB
Supported Languagesen
Quantization Type8bit
Model ArchitectureAutoModel
Licensecc
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|k_proj|v_proj|o_proj
LoRA Alpha16
LoRA Dropout0.1
R Param16

Best Alternatives to Medalpaca Lora 30B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Nemotron Labs Audex 30B A3B0K /  GB064
Yayi2 30B Llama GGUF0K / 12.9 GB39110
...e Llama 30B Instruct 2048 GGUF0K / 13.5 GB8654
VicUnlocked 30B LoRA GGUF0K / 13.5 GB8431
Platypus 30B GGUF0K / 13.5 GB5291
LLaMA 30B GGUF0K / 13.5 GB3835
Hippogriff 30B Chat GGUF0K / 13.5 GB2241
Llama 30B Supercot GGUF0K / 13.5 GB2290
Tulu 30B GGUF0K / 13.5 GB2130
30B Epsilon GGUF0K / 13.5 GB2084
Note: green Score (e.g. "73.2") means that the model is better than medalpaca/medalpaca-lora-30b-8bit.

Rank the Medalpaca Lora 30B 8bit 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? 54898 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