Steffen Röcker PRO

sroecker's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 13 hours ago

8GB VRAM Local LLMs - Practitioner Tested

Collection

Real practitioner benchmarks of small/mid open-source LLMs on consumer 8GB VRAM hardware (RTX 4060 Ti). • 4 items • Updated about 14 hours ago • 3

upvoted a collection 1 day ago

Granite 4.1 Language Models

Collection

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows. • 6 items • Updated 7 days ago • 45

upvoted an article 1 day ago

view article

Article

Granite 4.1 LLMs: How They’re Built

• 

7 days ago

•

61

upvoted a collection 1 day ago

APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 27 items • Updated 7 days ago • 87

upvoted a collection 3 days ago

1930 Coder

Collection

Fine-tuning the Talkie 13B 1930 model on agentic trajectories • 4 items • Updated about 7 hours ago • 4

upvoted a collection 5 days ago

Qwen3.6

Collection

4 items • Updated 14 days ago • 307

upvoted 3 collections 8 days ago

Laguna XS.2

Collection

Designed for agentic coding and long-horizon work on a local machine. Apache 2.0. • 4 items • Updated 8 days ago • 18

privacy-filter

Collection

OpenAI's privacy-filter fine0tuned models • 6 items • Updated 2 days ago • 8

talkie-13b

Collection

talkie-1930-13b is a vintage language model trained on pre-1931 English-language text. See https://github.com/talkie-lm/talkie to run talkie. • 3 items • Updated 15 days ago • 45

upvoted a collection 10 days ago

DeepSeek V4

Collection

8 items • Updated 11 days ago • 7

upvoted 2 collections 12 days ago

DeepSeek-V4

Collection

4 items • Updated 12 days ago • 613

DR-Venus

Collection

5 items • Updated 12 days ago • 17

upvoted a paper 14 days ago

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

Paper • 2411.17525 • Published Nov 26, 2024 • 6

upvoted a collection 14 days ago

HIGGS

Collection

Models prequantized with [HIGGS](https://arxiv.org/abs/2411.17525) zero-shot quantization. Requires the latest `transformers` to run. • 18 items • Updated Feb 18 • 15

upvoted an article 15 days ago

view article

Article

AI and the Future of Cybersecurity: Why Openness Matters

• 
• 
• +1

15 days ago

•

36

upvoted a collection 16 days ago

Kimi K2.5

Collection

Moonshot's most powerful model • 3 items • Updated 16 days ago • 65

upvoted a paper 19 days ago

TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification

Paper • 2604.14531 • Published 20 days ago • 7

upvoted a collection 19 days ago

Ternary Bonsai

Collection

1.58-bit Bonsai models • 9 items • Updated 15 days ago • 82

upvoted an article 20 days ago

view article

Article

The PR you would have opened yourself

• 
• 

20 days ago

•

68

upvoted a paper 20 days ago

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Paper • 2604.09497 • Published 26 days ago • 29