Furkan Nar

FurkanNar

TheOfficialFurkanNar

AI & ML interests

Deep learning

Recent Activity

liked a model about 7 hours ago

Qwen/Qwen3-Coder-Next

reacted to danielhanchen's post with 🔥 11 days ago

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗 Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

updated a dataset 27 days ago

FurkanNar/StackMathematics

View all activity

Organizations

None yet

liked a model about 7 hours ago

Qwen/Qwen3-Coder-Next

Text Generation • Updated 19 days ago • 434k • • 954

reacted to danielhanchen's post with 🔥 11 days ago

Post

5121

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

1 reply

updated a dataset 27 days ago

FurkanNar/StackMathematics

Viewer • Updated 27 days ago • 100 • 37 • 1

liked a dataset 27 days ago

FurkanNar/StackMathematics

Viewer • Updated 27 days ago • 100 • 37 • 1

published a dataset 27 days ago

FurkanNar/StackMathematics

Viewer • Updated 27 days ago • 100 • 37 • 1

upvoted 8 papers 30 days ago

Learning to Discover at Test Time

Paper • 2601.16175 • Published about 1 month ago • 42

SimpleMem: Efficient Lifelong Memory for LLM Agents

Paper • 2601.02553 • Published Jan 5 • 37

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Paper • 2510.14528 • Published Oct 16, 2025 • 118

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Paper • 2601.07372 • Published Jan 12 • 41

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Paper • 2601.16208 • Published about 1 month ago • 52

Efficient Memory Management for Large Language Model Serving with PagedAttention

Paper • 2309.06180 • Published Sep 12, 2023 • 37

VibeVoice Technical Report

Paper • 2508.19205 • Published Aug 26, 2025 • 143

MemOS: A Memory OS for AI System

Paper • 2507.03724 • Published Jul 4, 2025 • 159

liked a Space about 1 month ago

FLUX.2 [Klein] 9B

💻

538

Generate or edit images from text prompts with optional input images

upvoted a collection about 2 months ago

MobileLLM

Collection

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 50 items • Updated Dec 11, 2025 • 137

liked a model 3 months ago

deepseek-ai/DeepSeek-V3.2

Text Generation • Updated Dec 1, 2025 • 250k • • 1.25k

reacted to danielhanchen's post with 🔥 3 months ago

Post

3881

Mistral's new Ministral 3 models can now be Run & Fine-tuned locally! (16GB RAM)
Ministral 3 have vision support and the best-in-class performance for their sizes.
14B Instruct GGUF: unsloth/Ministral-3-14B-Instruct-2512-GGUF
14B Reasoning GGUF: unsloth/Ministral-3-14B-Reasoning-2512-GGUF

🐱 Step-by-step Guide: https://docs.unsloth.ai/new/ministral-3
All GGUFs, BnB, FP8 etc. variants uploads: https://huggingface.co/collections/unsloth/ministral-3