Rasmus Aagaard

rasgaard's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article about 13 hours ago

view article

Article

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

• 
• 

Aug 17, 2022

•

127

upvoted a collection 1 day ago

Qwen3.5

Collection

21 items • Updated about 9 hours ago • 830

liked a dataset 5 days ago

CoRal-project/coral-v3

Viewer • Updated 8 days ago • 468k • 592 • 2

updated a dataset 5 days ago

rasgaard/fleurs_test

Viewer • Updated 5 days ago • 14.4k • 42

published a dataset 5 days ago

rasgaard/fleurs_test

Viewer • Updated 5 days ago • 14.4k • 42

upvoted an article 11 days ago

view article

Article

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

• 
• 
• +4

12 days ago

•

473

upvoted an article 12 days ago

view article

Article

I Let a Lobster Run My Jetson: What OpenClaw Taught Me About the Future of Computing

• 

12 days ago

•

15

liked a model 14 days ago

syvai/plapre-nano

Text-to-Speech • 0.3B • Updated 14 days ago • 1.89k • 14

liked a model 15 days ago

thivy/embeddinggemma-300m-norwegian-health

Feature Extraction • 0.3B • Updated 15 days ago • 38 • 2

upvoted an article 21 days ago

view article

Article

Transformers.js v4 Preview: Now Available on NPM!

• 
• 

23 days ago

•

73

upvoted an article 23 days ago

view article

Article

From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output

• 

24 days ago

•

21

upvoted a paper 27 days ago

Beyond Transcription: Mechanistic Interpretability in ASR

Paper • 2508.15882 • Published Aug 21, 2025 • 87

liked a Space 27 days ago

Running

7

EuroEval Leaderboard

📊

7

The robust European language model benchmark.

upvoted an article 28 days ago

view article

Article

Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach

• 

Nov 24, 2024

•

20

upvoted a paper 29 days ago

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Paper • 2601.22813 • Published Jan 30 • 57

upvoted an article about 1 month ago

view article

Article

SmolLM-Smashed: Tiny Giants, Optimized for Speed

• 

Jan 13

•

14

liked 2 Spaces about 1 month ago

Running

664

AI Deadlines

⚡

664

Track upcoming AI conference and workshop deadlines

Running

Featured

44

Pocket TTS ONNX Web Demo

🌖

44

Real-time voice cloning entirely in your browser! (CPU)

upvoted a collection about 1 month ago

State-of-the-art Danish Models

Collection

These models constitute state-of-the-art models for Danish within their respective domain (highlighted below the model). • 18 items • Updated Nov 4, 2025 • 18

upvoted an article about 1 month ago

view article

Article

Slashing torch.compile Warmup & LoRA Swapping Times with Pruna

• 

Jan 28

•

5