Hugging Face Blog

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Quantization-Aware Healing: a compressed, 4-bit mo...

1 month ago 21 Add to circle
Wire It, Run It, Deploy It: AI Workflows in Gradio

Wire It, Run It, Deploy It: AI Workflows in Gradio...

1 month ago 14 Add to circle
Measuring benchmark optimization in speech recognition

Measuring benchmark optimization in speech recogni...

1 month ago 12 Add to circle
Up to 3.2x Faster Inference with LFM2.5-DSpark

Up to 3.2x Faster Inference with LFM2.5-DSpark

1 month ago 21 Add to circle
LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation

LFM2.5 Q4\_0 Checkpoints from Quantization-Aware D...

1 month ago 25 Add to circle
How Much Memory Does Your Agent Actually Need?

How Much Memory Does Your Agent Actually Need?

1 month ago 25 Add to circle
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Multi-Vector (Late Interaction) Embedding Models w...

1 month ago 15 Add to circle
Same Cluster, 33 Points More Utilization: What Changed Was the Order

Same Cluster, 33 Points More Utilization: What Cha...

1 month ago 17 Add to circle
State of Open Models: Summer 2026 Observations

State of Open Models: Summer 2026 Observations

1 month ago 17 Add to circle
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

Record, train, and deploy from one place with Stra...

1 month ago 28 Add to circle
What We Learned by Reproducing 2,200 papers from ICML

What We Learned by Reproducing 2,200 papers from I...

1 month ago 15 Add to circle
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis

Introducing OlmoEarth embeddings: Custom embedding...

1 month ago 15 Add to circle
LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

LFM2.5-VL-3B for Better and Faster Vision Capabili...

1 month ago 23 Add to circle
Thinking of ACE? We Can Do It with Fewer Tokens

Thinking of ACE? We Can Do It with Fewer Tokens

1 month ago 24 Add to circle
Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

Build Low-Latency Multilingual Voice Agents: Open ...

1 month ago 23 Add to circle
Making Knowledge Distillation Cheap Enough to Run at Scale

Making Knowledge Distillation Cheap Enough to Run ...

1 month ago 26 Add to circle
TutorMoments: Do AI tutors know when to help and when to hold back?

TutorMoments: Do AI tutors know when to help and w...

2 months ago 25 Add to circle
Baseten on Hugging Face Inference Providers 🔥

Baseten on Hugging Face Inference Providers 🔥

2 months ago 20 Add to circle

Trending

1. Joann's closing
2. Texas Tech basketball
3. UNC basketball
4. Ketamine
5. Monster Hunter Wilds
6. UPMC Memorial shooting
7. Macron
8. Hims stock
9. Apple 500 billion investment
10. Joel Embiid

Popular

I think I found a planet nobody knew existed. I used Claude Code to find it

I think I found a planet nobody knew existed. I used Claude ...

22 hours ago 14
AI startup Manus raises $500 million in first funding round since Meta breakup

AI startup Manus raises $500 million in first funding round ...

22 hours ago 7
Russia's internet giant Yandex halts operations at major data center after drone attack

Russia's internet giant Yandex halts operations at major dat...

21 hours ago 6
Ask Steve Webb your pension question for a special This is Money podcast

Ask Steve Webb your pension question for a special This is M...

20 hours ago 6
Sources: Flock plans to let go of ~270 employees, or 18% of its staff, at the end of October; the layoffs come after a voluntary buyout program in September (Reuters)

Sources: Flock plans to let go of ~270 employees, or 18% of ...

4 hours ago 6
English (US) English (US)
About Us · Contact Us · Terms & Conditions ·

© Inxa.inSearch.cc 2026. All rights are reserved