Steffen Röcker's picture

Steffen Röcker PRO

sroecker

·

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

liked a model 15 days ago

bartowski/mistralai_Devstral-Small-2-24B-Instruct-2512-GGUF

liked a model 15 days ago

EssentialAI/rnj-1-instruct

upvoted an article 21 days ago

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

View all activity

Organizations

upvoted an article 21 days ago

Article

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

21 days ago

•

62

upvoted an article 28 days ago

Article

Continuous batching from first principles

+1

about 1 month ago

•

283

upvoted 2 collections about 1 month ago

Speculator Models

14 items • Updated 6 days ago • 6

The Bestiary

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16 • 75

upvoted an article about 2 months ago

Article

Granite 4.0 Nano: Just how small can you go?

Oct 28

•

121

upvoted a collection about 2 months ago

Granite 4.0 Nano Language Models

9 items • Updated Nov 17 • 92

upvoted a collection 3 months ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated Sep 24 • 21

upvoted a collection 4 months ago

Gemma 3-270m

Collection of models for Gemma 3-270m • 4 items • Updated 9 days ago • 21

upvoted 5 collections 5 months ago

Qwen3-Coder

5 items • Updated Jul 31 • 141

GPT OSS

2 items • Updated 9 days ago • 13

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7 • 392

SauerkrautLM-Multilingual-(Reason)-ColBERT

SauerkrautLM ColBERT is a suite of Late-Interaction retrieval models built with PyLate’s ColBERT architecture and tuned for seven European languages. • 7 items • Updated Aug 3 • 20

🧩 July 2025 - Open works from the Chinese community

39 items • Updated Nov 20 • 8

upvoted an article 5 months ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

+3

Jul 29

•

205

upvoted 2 collections 5 months ago

GLM-4.5

GLM-4.5: An open-source large language model designed for intelligent agents by Z.ai • 11 items • Updated Aug 11 • 250

NuExtract-2.0

Models specialized in extracting structured information (JSON) from text, PDFs, scans, spreadsheets, etc. • 15 items • Updated Sep 26 • 26

upvoted 2 articles 5 months ago

Article

Ettin Suite: SoTA Paired Encoders and Decoders

+4

Jul 16

•

77

Article

Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.

Jul 16

•

147

upvoted a collection 6 months ago

Qwen3 Quantized

Collection of quantized Qwen 3 models from Alibaba Cloud. • 14 items • Updated Nov 10 • 7

upvoted an article 6 months ago

Article

Combining Remote Reasoning with Local Models

Jun 26

•

12