Allan Schramm

sharkdyt

·

https://ailocal.com.br/

AI & ML interests

The future of AI is Local and the harness matters more than the model.

Recent Activity

liked a model about 14 hours ago

deepgrove/maple-preview-GGUF

liked a model about 14 hours ago

ai9stars/G9v3-3B

liked a model about 24 hours ago

LiquidAI/LFM2.5-2.6B

View all activity

Organizations

upvoted 4 papers 4 days ago

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 9 days ago • 268

AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

Paper • 2607.28618 • Published 8 days ago • 298

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published 16 days ago • 309

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 11 days ago • 477

upvoted a collection 10 days ago

Instella-MoE ✨

Family of fully open 16B MoE LLM with 2.8B active params per token, trained on AMD Instinct™ MI300 & MI325 GPUs. • 6 items • Updated 9 days ago • 17

upvoted a collection 11 days ago

POCKET-MODELs

9 items • Updated 11 days ago • 24

upvoted 2 collections 14 days ago

💧 LFM2.5

Collection of post-trained and base LFM2.5 models. • 16 items • Updated 2 days ago • 188

Laguna XS 2.1

Designed for agentic coding and long-horizon work on a local machine. Licensed under OpenMDW-1.1. • 9 items • Updated Jul 2 • 23

upvoted an article 18 days ago

Article

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

ResterChed

•

20 days ago

• 194

upvoted 3 papers 20 days ago

TradingAgents: Multi-Agents LLM Financial Trading Framework

Paper • 2412.20138 • Published Dec 28, 2024 • 118

Orca: The World is in Your Mind

Paper • 2606.30534 • Published Jun 29 • 476

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published 22 days ago • 105

upvoted a paper 21 days ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 24 days ago • 232

upvoted a paper 22 days ago

AutoDev: Automated AI-Driven Development

Paper • 2403.08299 • Published Mar 13, 2024 • 19

upvoted a collection 22 days ago

Bonsai 27B

10 items • Updated 23 days ago • 214

upvoted a collection 23 days ago

NVFP4

Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 10 items • Updated 2 days ago • 53

upvoted 4 papers 24 days ago

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

Paper • 2607.04439 • Published Jul 5 • 63

RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue

Paper • 2607.01213 • Published Jul 1 • 5

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published May 22 • 264

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

Paper • 2606.03264 • Published Jun 2 • 27