Native bitsandbytes 4bit pre quantized models
Unsloth AI
company
AI & ML interests
Hey! We're focusing on making AI more accessible to everyone!
Organization Card
About org cards
🦥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 (8B) | ▶️ Start on Colab | 2x faster | 60% less |
| Gemma 2 (9B) | ▶️ Start on Colab | 2x faster | 63% less |
| Mistral v0.3 (7B) | ▶️ Start on Colab | 2.2x faster | 73% less |
| Phi-3 (mini) | ▶️ Start on Colab | 2x faster | 50% less |
Collections
2
-
unsloth/llama-3-8b-Instruct-bnb-4bit
Text Generation • Updated • 482k • 103 -
unsloth/mistral-7b-instruct-v0.2-bnb-4bit
Text Generation • Updated • 47.4k • 26 -
unsloth/mistral-7b-instruct-v0.3-bnb-4bit
Text Generation • Updated • 25.7k • 13 -
unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Text Generation • Updated • 64.3k • 16
models
94
unsloth/Phi-3-mini-4k-instruct-v0-bnb-4bit
Text Generation
•
Updated
•
41
•
1
unsloth/Phi-3-mini-4k-instruct
Text Generation
•
Updated
•
15.1k
•
31
unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Text Generation
•
Updated
•
64.3k
•
16
unsloth/Phi-3-mini-4k-instruct-v0
Text Generation
•
Updated
•
76
unsloth/gemma-2-9b
Text Generation
•
Updated
•
255
•
5
unsloth/gemma-2-27b-bnb-4bit
Text Generation
•
Updated
•
649
•
5
unsloth/gemma-2-27b
Text Generation
•
Updated
•
27
•
4
unsloth/gemma-2-9b-it
Text Generation
•
Updated
•
442
•
1
unsloth/gemma-2-9b-it-bnb-4bit
Text Generation
•
Updated
•
715
•
3
unsloth/gemma-2-27b-it-bnb-4bit
Text Generation
•
Updated
•
222