Valeriy Selitskiy's picture

Open to Work

Valeriy Selitskiy PRO

WaveCut

·

AI & ML interests

Looking to switch from hobby to career

Recent Activity

liked a model about 4 hours ago

WaveCut/Gemma-4-96E-A4B-Heretic-TQ

updated a model about 5 hours ago

WaveCut/Gemma-4-96E-A4B-Heretic-TQ

published a model about 5 hours ago

WaveCut/Gemma-4-96E-A4B-Heretic-TQ

View all activity

Organizations

upvoted an article 2 days ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

3 days ago

•

503

upvoted a collection 3 days ago

Trinity-Large-Thinking

4 items • Updated 3 days ago • 18

upvoted 3 collections 4 days ago

Bonsai

1-bit Bonsai models • 6 items • Updated 4 days ago • 136

💧 LFM2.5

Collection of post-trained and base LFM2.5 models. • 30 items • Updated 4 days ago • 121

Holo3

1 item • Updated 4 days ago • 32

upvoted 2 collections 11 days ago

AutoGaze

7 items • Updated 16 days ago • 9

GigaChat 3.1

6 items • Updated 12 days ago • 53

upvoted a collection 17 days ago

TranslateGemma

3 items • Updated 24 days ago • 226

upvoted 2 collections 19 days ago

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated 19 days ago • 63

Helios

Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated 20 days ago • 25

upvoted a collection 24 days ago

MiroThinker-1.7

2 items • Updated 24 days ago • 54

upvoted an article 25 days ago

Article

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

25 days ago

•

38

upvoted 5 collections about 1 month ago

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled

18 items • Updated 4 days ago • 184

IQuest-Coder

14 items • Updated Mar 3 • 107

Jan-code

2 items • Updated Mar 2 • 19

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated about 7 hours ago • 128

Quantized Qwen3.5

Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. • 9 items • Updated 23 days ago • 9

upvoted a paper about 1 month ago

The Free Transformer

Paper • 2510.17558 • Published Oct 20, 2025 • 6

upvoted 2 collections about 1 month ago

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 28 items • Updated 21 days ago • 153

ParoQuant

Pairwise Rotation Quantization for Efficient Reasoning LLM Inference • 17 items • Updated 7 days ago • 15