Native bitsandbytes 4bit pre quantized models
Unsloth AI
Enterprise
company
AI & ML interests
Hey! We're focusing on making AI more accessible to everyone!
Organization Card
🦥Unsloth makes fine-tuning of LLMs 2.2x faster and use 80% less VRAM!
Join our Discord server! Our open source Github: https://github.com/unslothai/unsloth
Unsloth support includes | Free Notebooks | Performance | Memory use |
---|---|---|---|
Llama 3.1 (8B) | ▶️ Start on Colab | 2.1x faster | 60% less |
Gemma 2 (9B) | ▶️ Start on Colab | 2x faster | 63% less |
Mistral Nemo (12B) | ▶️ Start on Colab | 2x faster | 60% less |
Phi-3.5 (mini) | ▶️ Start on Colab | 2x faster | 50% less |
Collections
2
-
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Text Generation • Updated • 274k • 35 -
unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit
Text Generation • Updated • 13k • 16 -
unsloth/llama-3-8b-Instruct-bnb-4bit
Text Generation • Updated • 769k • 123 -
unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Text Generation • Updated • 30.5k • 24
models
174
unsloth/Qwen2.5-3B
Text Generation
•
Updated
•
38
unsloth/Qwen2.5-3B-bnb-4bit
Text Generation
•
Updated
•
221
•
1
unsloth/Qwen2.5-1.5B-bnb-4bit
Text Generation
•
Updated
•
72
unsloth/Qwen2.5-1.5B
Text Generation
•
Updated
•
143
unsloth/Qwen2.5-0.5B
Text Generation
•
Updated
•
66
unsloth/Qwen2.5-0.5B-bnb-4bit
Text Generation
•
Updated
unsloth/SmolLM-360M-bnb-4bit
Text Generation
•
Updated
•
65
unsloth/SmolLM-360M
Text Generation
•
Updated
•
6
unsloth/SmolLM-360M-Instruct-bnb-4bit
Text Generation
•
Updated
•
13
unsloth/SmolLM-360M-Instruct
Text Generation
•
Updated
•
8