Steffen Röcker's picture

Steffen Röcker PRO

sroecker

·

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

liked a model 1 day ago

RedHatAI/MiniMax-M2.5

liked a model 2 days ago

EganAI/qwen3.5-9b-terminal-merge

liked a model 3 days ago

Ex0bit/Qwen3.5-PRISM-Dynamic-Quant-GGUF

View all activity

Organizations

upvoted a collection 5 days ago

Quantized Qwen3.5

Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. • 10 items • Updated 3 days ago • 8

upvoted 2 collections 9 days ago

Qwen3-MoE

Compressed Qwen3 MoE models with a reduced number of experts. See additional models at https://huggingface.co/bknyaz. • 9 items • Updated 23 days ago • 3

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 9 days ago • 129

upvoted a collection 10 days ago

Qwen3.5

21 items • Updated 3 days ago • 992

upvoted a collection 14 days ago

gliner2 family

GLiNER2 extends the original GLiNER architecture to support multi-task information extraction with a schema-driven interface. This base model provid • 4 items • Updated 24 days ago • 34

upvoted a collection 18 days ago

QED Nano

Artifacts for the QED Nano release • 9 items • Updated 4 days ago • 7

upvoted an article 26 days ago

Article

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

27 days ago

•

21

upvoted a collection about 1 month ago

ZeroShot

Collection of LLMs finetuned for bughunting • 2 items • Updated Jan 20 • 2

upvoted 2 articles 3 months ago

Article

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

Dec 4, 2025

•

65

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

341

upvoted 2 collections 4 months ago

Speculator Models

12 items • Updated 4 days ago • 7

The Bestiary

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16, 2025 • 100

upvoted an article 4 months ago

Article

Granite 4.0 Nano: Just how small can you go?

Oct 28, 2025

•

123

upvoted a collection 4 months ago

Granite 4.0 Nano Language Models

9 items • Updated Nov 17, 2025 • 97

upvoted a collection 5 months ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated Jan 29 • 22

upvoted 5 collections 7 months ago

Gemma 3-270m

Collection of models for Gemma 3-270m • 4 items • Updated Dec 16, 2025 • 21

Qwen3-Coder

5 items • Updated Dec 31, 2025 • 169

GPT OSS

2 items • Updated Dec 16, 2025 • 14

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 417

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, 2025 • 20