Jakub Povinec

kuko6

·

https://jpovinec.me

AI & ML interests

Computer Vision

Recent Activity

liked a model 10 days ago

abenzerps/Qwen-Image-2.1-Uncensored-GGUF

liked a model 15 days ago

Altworld/Hemmingway-1

liked a model 16 days ago

convaiinnovations/laya

View all activity

Organizations

None yet

upvoted a collection 20 days ago

Cactus Needle

Automation Foundation Models For Tiny Devices • 3 items • Updated 6 days ago • 9

upvoted a collection about 2 months ago

Ornith-1.5

13 items • Updated 19 days ago • 185

upvoted a collection 4 months ago

Bonsai Image

6 items • Updated Jun 4 • 97

upvoted an article 6 months ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 930

upvoted a collection 6 months ago

Gemma 4

Our most intelligent open models to date • 16 items • Updated 9 days ago • 1.15k

upvoted 2 collections 8 months ago

KittenTTS

All MLX conversions of KittenTTS (nano/micro/mini) across fp32, fp16, bf16, and 4/5/6/8-bit quantizations. • 21 items • Updated Feb 24 • 5

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 481

upvoted a collection 9 months ago

Qwen3-TTS

7 items • Updated Jan 22 • 398

upvoted a changelog about 1 year ago

Hugging Face Changelog

Introducing HF Jobs: Run scalable compute jobs on Hugging Face

Jul 30, 2025

• 206

upvoted a collection about 1 year ago

Gemma 3

A collection of lightweight, state-of-the-art open models built from the same research and technology that powers the Gemini 2.0 models • 42 items • Updated Aug 14, 2025 • 33

upvoted 4 collections over 1 year ago

Kokoro TTS

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers amazing quality. • 4 items • Updated Feb 28, 2025 • 11

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 29 items • Updated Aug 14, 2025 • 32

Google's Gemma models family

334 items • Updated Jul 21 • 857

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5, 2025 • 314

upvoted 2 articles over 1 year ago

Article

SmolVLM - small yet mighty Vision Language Model

+3

andito, merve, mfarre, eliebak, pcuenq

•

Nov 26, 2024

• 433

Article

SmolLM - blazingly fast and remarkably powerful

+1

loubnabnl, anton-l, eliebak

•

Jul 16, 2024

• 470

upvoted a collection about 2 years ago

Whisper

OpenAI Whisper speech recognition models in MLX format • 48 items • Updated Oct 1, 2024 • 71