Daniel (Unsloth)'s picture

Daniel (Unsloth) PRO

danielhanchen

·

https://unsloth.ai/

AI & ML interests

None yet

Recent Activity

published a Space about 5 hours ago

posted an update about 5 hours ago

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: https://github.com/unslothai/unsloth Blog and Guide: https://unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

new activity about 11 hours ago

unsloth/Mistral-Small-4-119B-2603-GGUF:UD-Q4_K_M 404ed

View all activity

Organizations

upvoted a collection 8 days ago

Agentic RL Hackathon (SF) 2026

158 items • Updated 6 days ago • 6

upvoted an article 13 days ago

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

+5

Feb 4

•

88

upvoted an article 19 days ago

Article

Mixture of Experts (MoEs) in Transformers

+5

20 days ago

•

135

upvoted a collection 21 days ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 6 days ago • 114

upvoted an article 25 days ago

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

+4

26 days ago

•

487

upvoted an article 26 days ago

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

+4

26 days ago

•

86

upvoted an article about 2 months ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

Dec 1, 2025

•

306

upvoted 2 collections 3 months ago

Unsloth Diffusion GGUFs

Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX. • 20 items • Updated 6 days ago • 60

Magic Quant

Hybrid GGUF quants created via an evolutionary quant algorithm. Want the best TPS? Lowest precision loss? Smallest file size? Welcome to MagicQuant! • 7 items • Updated 15 days ago • 28

upvoted a collection 4 months ago

Ministral 3

Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. • 36 items • Updated 6 days ago • 30

upvoted an article 4 months ago

Article

Introducing Cogito v2.1

Nov 19, 2025

•

17

upvoted a paper 5 months ago

Efficient Long-context Language Model Training by Core Attention Disaggregation

Paper • 2510.18121 • Published Oct 20, 2025 • 123

upvoted a paper 10 months ago

Speechless: Speech Instruction Training Without Speech for Low Resource Languages

Paper • 2505.17417 • Published May 23, 2025 • 14

upvoted a collection 10 months ago

TorchAO Quantized Phi-4-mini-instruct

TorchAO quantized Phi-4-mini-instruct models from PyTorch team, runnable in A100, H100 through vLLM and in mobile devices through ExecuTorch • 7 items • Updated Dec 16, 2025 • 3

upvoted a collection 11 months ago

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 80 items • Updated 6 days ago • 469

upvoted an article 11 months ago

Article

Comparing sub 50GB Llama 4 Scout quants (KLD/Top P)

Apr 9, 2025

•

45

upvoted a collection 12 months ago

Qwen2.5-VL (All Versions)

All versions of Qwen2.5-VL including the new 32B version and 4-bit, 16-bit and more! • 16 items • Updated 6 days ago • 22

upvoted 2 collections about 1 year ago

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 6 days ago • 266

Phi-4 (All Versions)

Microsoft's Phi-4 models including Reasoning + Reasoning Plus & mini. Includes Dynamic 2.0 GGUF, 4-bit & 16-bit versions. Includes Unsloth's bug fixes • 20 items • Updated 6 days ago • 80

upvoted a collection over 1 year ago

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 • 28 items • Updated 6 days ago • 94