Orion LLM Labs

community

Activity Feed Request to join this org

AI & ML interests

We are committed to advancing the field of AGI by pushing the boundaries of local LLM inference efficiency.

Recent Activity

DedeProGames new activity about 11 hours ago

OrionLLM/OpenAgentInstruct:What is the source of the data?

DedeProGames new activity about 19 hours ago

OrionLLM/GRM-2.6-Plus:Great job! Any plan to create a GRM model based on Qwen3.6-35b-A3B? So that 16gb vram can run it.

DedeProGames updated a collection 1 day ago

GRM-2.6

View all activity

DedeProGames

in OrionLLM/OpenAgentInstruct about 11 hours ago

What is the source of the data?

#2 opened 15 days ago by

pedrodev2026

DedeProGames

posted an update about 15 hours ago

Post

2530

🚀 Introducing the GRM-2.6 Family

The GRM-2.6 family is a new generation of reasoning-focused models from Orion LLM Labs, built for difficult tasks, coding, STEM, terminal agents, and advanced local AI workflows.

GRM-2.6-Plus is the main high-capability model in the family: a 27B-class reasoning model based on Qwen3.6, designed for strong structured reasoning, coding, agentic use, and practical local deployment.

GRM-2.6-Opus builds on GRM-2.6-Plus as a merge with an Opus-style reasoning distilled model, improving structured reasoning behavior, terminal-agent workflows, coding ability, and complex problem solving.

Both models are designed for users who want powerful reasoning models that remain practical for research, local inference, coding, and agent experiments.

Models:
GRM-2.6-Plus: OrionLLM/GRM-2.6-Plus
GRM-2.6-Opus: OrionLLM/GRM-2.6-Opus

Organization:

OrionLLM

DedeProGames

in OrionLLM/GRM-2.6-Plus about 19 hours ago

Great job! Any plan to create a GRM model based on Qwen3.6-35b-A3B? So that 16gb vram can run it.

#4 opened about 23 hours ago by

cmy2019

DedeProGames

updated a collection 1 day ago

GRM-2.6

Collection

2 items • Updated 1 day ago • 2

DedeProGames

updated a model 1 day ago

OrionLLM/GRM-2.6-Opus

Image-Text-to-Text • 28B • Updated 1 day ago • 50 • 6

DedeProGames

published a model 1 day ago

OrionLLM/GRM-2.6-Opus

Image-Text-to-Text • 28B • Updated 1 day ago • 50 • 6

DedeProGames

updated a model 1 day ago

OrionLLM/GRM-2.6-Plus

Image-Text-to-Text • 28B • Updated 1 day ago • 924 • 36

DedeProGames

posted an update 4 days ago

Post

8488

GRaPE 2 Pro is now available.

SL-AI/GRaPE-2-Pro

This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.

GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the tag. This gives you real control over how hard the model thinks, from skipping the reasoning phase entirely with minimal, all the way up to xtra-Hi for deep, extended thought on hard problems. For most agentic use, auto or low is the move to keep things snappy.

It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.

If you want to try it out and give feedback, that would be really appreciated. Email us at contact@skinnertopia.com