Steffen Röcker's picture

Steffen Röcker PRO

sroecker

·

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

upvoted an article about 18 hours ago

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

liked a model 1 day ago

nvidia/Kimi-K2.5-Thinking-Eagle3

liked a model 1 day ago

Tesslate/OmniCoder-9B

View all activity

Organizations

upvoted an article about 18 hours ago

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

+7

4 days ago

•

43

upvoted a collection 3 days ago

Distil Efficiency Benchmarks

Collection of models used in the blog post www.distillabs.ai/blog/the-10x-inference-tax-you-dont-have-to-pay • 9 items • Updated 12 days ago • 3

upvoted a collection 13 days ago

Quantized Qwen3.5

Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. • 9 items • Updated 1 day ago • 9

upvoted a collection 16 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 about 1 month ago • 3

upvoted 2 collections 17 days ago

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 17 days ago • 130

Qwen3.5

21 items • Updated 4 days ago • 1.16k

upvoted a collection 22 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 Feb 10 • 38

upvoted a collection 25 days ago

QED Nano

Artifacts for the QED Nano release • 9 items • Updated 12 days ago • 8

upvoted an article about 1 month ago

Article

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

Feb 7

•

22

upvoted a collection about 2 months ago

ZeroShot

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

upvoted an article 3 months ago

Article

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

Dec 4, 2025

•

66

upvoted an article 4 months ago

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

343

upvoted 2 collections 4 months ago

Speculator Models

12 items • Updated 12 days ago • 11

The Bestiary

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16, 2025 • 102

upvoted an article 5 months ago

Article

Granite 4.0 Nano: Just how small can you go?

Oct 28, 2025

•

123

upvoted a collection 5 months ago

Granite 4.0 Nano Language Models

9 items • Updated Nov 17, 2025 • 98

upvoted a collection 6 months ago

GLiNER-PII

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

upvoted 3 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 • 171

GPT OSS

2 items • Updated Dec 16, 2025 • 14