Daniel Han (@danielhanchen) / X

Daniel Han

3,581 posts

Daniel Han

@danielhanchen

Building @UnslothAI • Making open-source LLMs faster, better & more accessible • YC S24 • ex-NVIDIA ML

San Francisco

Joined April 2016

Pinned
Daniel Han
@danielhanchen
Mar 17
We're excited to introduce Unsloth🦥Studio! 1. Chat UI has auto healing tool calling, Python & bash code execution, web search, image, docs input + more! 2. Finetune audio, vision, LLMs with an AI Assist data prep 3. Supports GGUFs, Mac, Windows, Linux + audio gen 4. Has SVG
Unsloth AI
@UnslothAI
Mar 17
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 •
00:00
Daniel Han
@danielhanchen
Jul 21
My 2hr workshop on Open vs Closed models, reward hacking, benchmaxxing & RL is out! 1. Closed vs open models 2. Throughput maxxing but accuracy minimizing 3. Benchmaxxing & cheating 4. Distillation & RL 5. Stopping reward hacking 6. @UnslothAI Dynamic Quants Details: 1. If
Special Topics in Kernels, RL, Reward Hacking in Agents — Daniel Han, Unsloth
From youtube.com
Daniel Han
@danielhanchen
Jul 20
We worked with @AMD to add RL, inference, notebooks, 2x faster, 70% less VRAM training on over 500 models + more to Unsloth & Unsloth Studio! > RDNA 3-4, Strix Halo, MI300, 325 + more support > Windows, Linux, WSL support > RL vLLM weight sharing + faster > Free remote HTTPS!
Unsloth AI
@UnslothAI
Jul 20
Introducing Unsloth for AMD 🚀 You can now train & run LLMs on your AMD hardware • We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs • Works on Windows, WSL, Linux • Train Qwen, Gemma on 3GB VRAM GitHub: github.com/unslothai/unsl… Works on Radeon,
Daniel Han
@danielhanchen
Jul 15
We collabed with Thinking Machines to bring dynamic Unsloth 1-bit GGUF quants for Inkling to everyone! 86% smaller (270GB vs 1.9TB) yet it retains 74.2% of top-1% accuracy! We added vision and audio support as well! GGUFs and more at huggingface.co/unsloth/inklin…
Unsloth AI
@UnslothAI
Jul 15
You can now run Thinking Machines Inkling! Inkling is a 975B open model with image, audio and 1M context support. We quantized Inkling to Dynamic 1-bit (-86% size) and retained 74.2% of top-1% accuracy. Run on 280GB. Guide: unsloth.ai/docs/models/in… GGUF: huggingface.co/unsloth/inklin…
Daniel Han
@danielhanchen
Jul 14
More NVFP4 dynamic quants! We made them for all Gemma-4 sizes (E2B, E4B, 12B, 26B-A4B, 31B) - they're all W4A4 + FP8 KV cache calibrated + W8A8 for attention / important layers. We also made Qwen3.5-122B-A10B and GLM-4.7-Flash NVFP4 ones as well - 397B and others will come soon!
Unsloth AI
@UnslothAI
Jul 14
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU. Gemma-4-12B NVFP4 works on 11GB VRAM. 26B-A4B hits 13K tok/s (B200). Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference. Blog: unsloth.ai/docs/basics/nv… Gemma NVFP4: huggingface.co/collections/un…
See @danielhanchen's full profile
Sign up
Log in

See @danielhanchen's full profile

See @danielhanchen's full profile