gg-hf-em (gg-hf-em)

posted an update 8 days ago

Post

4,775

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

5 replies

·

danielhanchen

posted an update 10 days ago

Post

3,961

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

bebechien

updated a model 10 days ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 10 days ago • 144k • 2.42k

MaartenGr

in google/embeddinggemma-2 11 days ago

Update README.md

#3 opened 11 days ago by

hschechter

in google/embeddinggemma-2 11 days ago

Update README.md

#3 opened 11 days ago by

hschechter

Update README.md

#2 opened 11 days ago by

hschechter

MaartenGr

updated a model 11 days ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 10 days ago • 144k • 2.42k

hschechter

updated a model 12 days ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 10 days ago • 144k • 2.42k

danielhanchen

posted an update 21 days ago

Post

9,089

Unsloth has surpassed 500M model downloads on Hugging Face! 🦥🤗

Qwen3.8-27B GGUF is already Unsloth’s #1 most-downloaded model ever.

Thanks for all your support! Follow us:

unsloth

1 reply

·

jandonov

updated a model 21 days ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 10 days ago • 144k • 2.42k

danielhanchen

posted an update 24 days ago

Post

3,689

Qwen-Image-2.1 can now run locally on 12GB VRAM with Unsloth GGUFs! 🖼️

The 7B model performs on par with Nano Banana 2.0.

For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading.

GGUF: unsloth/Qwen-Image-2.1-GGUF
Guide: https://unsloth.ai/docs/models/qwen-image-2.1

danielhanchen

posted an update about 1 month ago

Post

6,874

Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time! 🤗🦥

The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.

GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8

5 replies

·

tomaarsen

posted an update about 2 months ago

Post

4,323

🚨 I've just published Sentence Transformers v6.0, introducing MultiVectorEncoder: ColBERT-style late interaction models are now a fourth model type, for training, inference, and interpretation, alongside the dense, sparse, and reranker models! Details:

Where a regular embedding model compresses a whole text into one vector, a multi-vector model keeps one vector per token and scores query against document with the MaxSim operator. That preserves token-level matching information that a single vector has to average away. It is also the state of the art for visual document retrieval, where a text query is matched against page images directly, charts and tables included, with no OCR step in between.

Any PyLate, Stanford ColBERT, or ColPali checkpoint loads straight into the same familiar API: model.encode_query(), model.encode_document(), and model.similarity() just work, whether the documents are texts or page images.

Does it help? LightOn trained LateOn (multi-vector) and DenseOn (dense) on the same data with the same 149M ModernBERT backbone, and the multi-vector model wins on 9 of the 13 NanoBEIR datasets: 0.6868 vs 0.6764 mean NDCG@10. The price is a bigger index, and the new HierarchicalTokenPooling module halves it at roughly no retrieval cost.

Antoine Chaffin, Raphaël Sourty, and I wrote a blog post walking through multi-vector models in practice: loading the various checkpoint formats, encoding and scoring, plugging them into a search stack, running them on page images, and keeping the index affordable. Check it out if you want to get started, or just point your Agent to the URL: https://huggingface.co/blog/multi-vector-encoder

pip install sentence-transformers==6.0.0

Release notes: https://github.com/huggingface/sentence-transformers/releases/tag/v6.0.0

danielhanchen

posted an update 2 months ago

Post

7,564

Introducing Unsloth Desktop 🦥
The first desktop app to run and train models locally.

• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere

Unsloth Desktop is now available on http://unsloth.ai
and GitHub.

GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/desktop

6 replies

·

danielhanchen

posted an update 2 months ago

Post

3,827

DeepSeek-V4-Flash can now run 2× faster locally with DSpark! ⚡️

DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2× faster with no accuracy change.

DeepSeek-V4-Flash-0731 can reach at 120 tokens/s.

GGUFs: unsloth/DeepSeek-V4-Flash-0731-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

danielhanchen

posted an update 3 months ago

Post

3,568

We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. 🤯

We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...

1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.

GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth

1 reply

·

danielhanchen

posted an update 3 months ago

Post

5,763

Kimi K3 can now be run locally! ✨

The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).

Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.

GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3