Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents
•
34
AI & ML interests
Enterprise-grade AI models
Recent Activity
View all activity
Papers
ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Articles
danielhanchen
posted an update 7 minutes ago
yousafshah
updated a
model 11 minutes ago
Update README.md
#3 opened about 2 hours ago
by 
aheching
Update README.md
#3 opened about 2 hours ago
by aheching
Update answerability/README.md
#46 opened about 14 hours ago
by 
alonfre
kristunlee
updated a
Space about 10 hours ago
daviddcox
published a
model 1 day ago
pengyuan
authored 3
papers 1 day ago
ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation
Paper • 2507.19492 • Published • 1
Composition-Grounded Instruction Synthesis for Visual Reasoning
Paper • 2510.15040 • Published
ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
Paper • 2603.27064 • Published • 27
danielhanchen
posted an update 6 days ago
Post
5183
Qwen3.6-27B is out now! Run it locally on 18GB RAM. 💜
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6
danielhanchen
posted an update 12 days ago
Post
2781
Qwen3.6-35B-A3B can now be run locally! 💜
The model is the strongest mid-sized LLM on nearly all benchmarks.
Run on 23GB RAM via Unsloth Dynamic GGUFs.
GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6
The model is the strongest mid-sized LLM on nearly all benchmarks.
Run on 23GB RAM via Unsloth Dynamic GGUFs.
GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6
- 13 replies
sanchy-ibm
authored a
paper 15 days ago
danielhanchen
posted an update 21 days ago
Post
5412
You can now fine-tune Gemma 4 for free with our notebooks! 🔥
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
- 5 replies
danielhanchen
posted an update 26 days ago
Post
3774
Google releases Gemma 4. ✨
Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B.
The multimodal reasoning models are under Apache 2.0.
Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4
Guide: https://unsloth.ai/docs/models/gemma-4
Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B.
The multimodal reasoning models are under Apache 2.0.
Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4
Guide: https://unsloth.ai/docs/models/gemma-4
danielhanchen
posted an update 28 days ago
Post
2741
A new way to use Unsloth.
Coming soon...
Coming soon...
ink-pad
authored 3
papers 30 days ago
Accelerating Material Design with the Generative Toolkit for Scientific Discovery
Paper • 2207.03928 • Published
Programming Refusal with Conditional Activation Steering
Paper • 2409.05907 • Published
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Paper • 2510.09781 • Published • 27