Hugging Face's logo

Unsloth AI

Enterprise
company
Verified
https://unsloth.ai
unslothai
unslothai
Activity Feed

AI & ML interests

Hey! We're focusing on making AI more accessible to everyone!

Recent Activity

shimmyshimmer  updated a Space about 14 hours ago
unsloth/README
shimmyshimmer  new activity 1 day ago
unsloth/DeepSeek-R1-GGUF:I tested dynamic 1.58bit and 2.22bit, All thoughts are empty?
shimmyshimmer  updated a model 3 days ago
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
View all activity

Organization Card
Community About org cards

🦥Unsloth makes fine-tuning of LLMs & Vision LMs 2.2x faster and use 80% less VRAM!

Join our Discord server! Our open source Github: https://github.com/unslothai/unsloth

Unsloth supports Free Notebooks Performance Memory use
GRPO (Reasoning) ▶️ Start for free 1.5x faster 80% less
Llama 3.2 (3B) ▶️ Start for free 2x faster 60% less
Phi-4 (14B) ▶️ Start for free 2x faster 50% less
Llama 3.2 Vision (11B) ▶️ Start for free 2x faster 40% less
Llama 3.1 (8B) ▶️ Start for free 2x faster 60% less
Qwen 2.5 (7B) ▶️ Start for free 2x faster 63% less
Mistral v0.3 (7B) ▶️ Start for free 2.2x faster 73% less

Collections 16

Unsloth 4-bit Dynamic Quants
Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit