Unsloth AI

Team

company

Verified

https://unsloth.ai

AI & ML interests

Run and train models via Unsloth Desktop 🦥

Recent Activity

danielhanchen updated a model about 6 hours ago

unsloth/LFM2.5-230M

danielhanchen updated a model about 6 hours ago

unsloth/ERNIE-4.5-21B-A3B-Thinking

danielhanchen updated a model about 6 hours ago

unsloth/ERNIE-4.5-21B-A3B-PT

View all activity

danielhanchen

updated 5 models about 6 hours ago

updated a model 1 day ago

unsloth/Qwen-Image-2.1-Turbo-GGUF

Text-to-Image • 7B • Updated 1 day ago • 50.5k • 31

danielhanchen

published a model 1 day ago

unsloth/Qwen-Image-2.1-Turbo-GGUF

Text-to-Image • 7B • Updated 1 day ago • 50.5k • 31

danielhanchen

updated a model 1 day ago

unsloth/Qwen-Image-2.1-Turbo-FP8

Text-to-Image • Updated 1 day ago • 6.23k • 18

danielhanchen

published a model 1 day ago

unsloth/Qwen-Image-2.1-Turbo-FP8

Text-to-Image • Updated 1 day ago • 6.23k • 18

shimmyshimmer

in unsloth/Qwen-Image-2.1-FP8 2 days ago

model_index.json

👍 2

#2 opened 18 days ago by

amaranus

danielhanchen

posted an update 3 days ago

Post

4357

You can now train your own Decision model like Jev locally!

We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.

Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.

GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth

4 replies

danielhanchen

updated a collection 4 days ago

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 123 items • Updated 4 days ago • 842

danielhanchen

in unsloth/embeddinggemma-2-GGUF 4 days ago

EmbeddingGemma 2 - Chat with Files, Fine-tune, use Semantic Search, RAG with Unsloth!

🤗❤️ 6

#2 opened 4 days ago by

danielhanchen

updated a model 4 days ago

unsloth/embeddinggemma-2-GGUF

Feature Extraction • 0.3B • Updated 4 days ago • 59.3k • 244

danielhanchen

posted an update 5 days ago

Post

3772

Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.

The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).

Run & train the model via Unsloth.

GGUF: unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2