Merlin-Research/Qwen3.5-4B-Safety-Thinking
Text Generation • 4B • Updated • 1.68k • 20
Merlin Research
non-profit
AI & ML interests
Independent AI safety lab. Stockholm, Sweden. We test deployed LLM agents under adversarial conditions and measure behavioral alignment in production — not in controlled benchmarks.
Recent Activity
View all activity
squ11z1
updated 3
models 5 days ago
squ11z1
published a
model 5 days ago
squ11z1
updated a
Space 5 days ago
squ11z1
published a
model 5 days ago
squ11z1
updated a
model 6 days ago
squ11z1
updated a
model 9 days ago
DedeProGames
posted an update 18 days ago
Post
271
Please give a follow to Orion LLM Labs.
We are researching to create the best models for local deployment.
OrionLLM/GRM-2.6-Plus
OrionLLM/GRM-2.7-Mythos
OrionLLM/GRM-OCR
We are researching to create the best models for local deployment.
OrionLLM/GRM-2.6-Plus
OrionLLM/GRM-2.7-Mythos
OrionLLM/GRM-OCR
DedeProGames
posted an update about 2 months ago
Post
347
🚀 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
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:
DedeProGames
posted an update 2 months ago
Post
5176
🚀 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
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:
- 2 replies
DedeProGames
posted an update 2 months ago
Post
8590
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
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
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
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 
- 1 reply
DedeProGames
posted an update 3 months ago
Post
3486
🔥 GRM-2.5 - The most POWERFUL model for local inference
The GRM-2.5 is the newest model from Orion LLM Labs. It has consistent RAW reasoning and is capable of generating very precise responses, similar to large models, while maintaining a parameter size of 4b.
The GRM-2.5 family consists of these models:
OrionLLM/GRM-2.5 (4b)
OrionLLM/GRM-2.5-Air (0.8b)
Furthermore, the GRM-2.5 is the best option for local agentic environments, being very good in code, terminal agent, etc. It is capable of generating 1000 lines of consistent code and programming like large models.
The GRM-2.5 is the best base for FineTune to date and has vision, which means it can interpret images and videos.
The GRM-2.5 is the newest model from Orion LLM Labs. It has consistent RAW reasoning and is capable of generating very precise responses, similar to large models, while maintaining a parameter size of 4b.
The GRM-2.5 family consists of these models:
OrionLLM/GRM-2.5 (4b)
OrionLLM/GRM-2.5-Air (0.8b)
Furthermore, the GRM-2.5 is the best option for local agentic environments, being very good in code, terminal agent, etc. It is capable of generating 1000 lines of consistent code and programming like large models.
The GRM-2.5 is the best base for FineTune to date and has vision, which means it can interpret images and videos.
- 1 reply
DedeProGames
posted an update 3 months ago
Post
3061
🔥 GRM2 - The small one that surpasses the big ones.
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
🤗 Model: OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
🚀 Chat with GRM:
https://huggingface.co/spaces/DedeProGames/GRM2-Chat
🏆 Download official GGUFs: OrionLLM/GRM2-3b-GGUF
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
🤗 Model: OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
🚀 Chat with GRM:
https://huggingface.co/spaces/DedeProGames/GRM2-Chat
🏆 Download official GGUFs: OrionLLM/GRM2-3b-GGUF
DedeProGames
posted an update 3 months ago
Post
1792
Introducing GRM2, a powerful 3 billion parameter model designed for long-term reasoning and high performance in complex tasks.
Even with only 3 billion parameters, it outperforms qwen3-32b in several benchmarks and complex reasoning tasks.
With just 3 billion parameters, it can also generate extensive and complex code with over 1000 lines, utilize tools comparable to larger models, and is perfect for agentic tasks.
GRM2 is licensed under Apache 2.0, making it ideal as a base for FineTune in other tasks.
GRM2 Model Page: OrionLLM/GRM2-3b
Official GRM2 GGUFs Quantizations: OrionLLM/GRM2-3b-GGUF
Even with only 3 billion parameters, it outperforms qwen3-32b in several benchmarks and complex reasoning tasks.
With just 3 billion parameters, it can also generate extensive and complex code with over 1000 lines, utilize tools comparable to larger models, and is perfect for agentic tasks.
GRM2 is licensed under Apache 2.0, making it ideal as a base for FineTune in other tasks.
GRM2 Model Page: OrionLLM/GRM2-3b
Official GRM2 GGUFs Quantizations: OrionLLM/GRM2-3b-GGUF
DedeProGames
posted an update 4 months ago
Post
193
Introducing GRM-Coder, a 14b params code model based on Qwen3-14b .
On LiveCodeBench v6 (01/08/2024 - 01/05/2025), we achieved a Pass@1 accuracy of 67.87%, up 7.08% from the baseline Pass@1 accuracy of 60.79% of Qwen3-14B.
OrionLLM/GRM-Coder-14b
On LiveCodeBench v6 (01/08/2024 - 01/05/2025), we achieved a Pass@1 accuracy of 67.87%, up 7.08% from the baseline Pass@1 accuracy of 60.79% of Qwen3-14B.
OrionLLM/GRM-Coder-14b
squ11z1
updated a
dataset 4 months ago
DedeProGames
posted an update 4 months ago
Post
5279
Introducing GRM2, a powerful 3 billion parameter model designed for long-term reasoning and high performance in complex tasks.
Even with only 3 billion parameters, it outperforms qwen3-32b in several benchmarks and complex reasoning tasks.
With just 3 billion parameters, it can also generate extensive and complex code with over 1000 lines, utilize tools comparable to larger models, and is perfect for agentic tasks.
GRM2 is licensed under Apache 2.0, making it ideal as a base for FineTune in other tasks.
You can see more here: OrionLLM/GRM2-3b
Even with only 3 billion parameters, it outperforms qwen3-32b in several benchmarks and complex reasoning tasks.
With just 3 billion parameters, it can also generate extensive and complex code with over 1000 lines, utilize tools comparable to larger models, and is perfect for agentic tasks.
GRM2 is licensed under Apache 2.0, making it ideal as a base for FineTune in other tasks.
You can see more here: OrionLLM/GRM2-3b
squ11z1
published a
model 4 months ago
DedeProGames
posted an update 4 months ago
Post
624
Introducing GRM2, a powerful 3b parameter model designed for long-term reasoning and high performance in complex tasks.
Even with only 3b of parameters, it outperforms qwen3-32b in several benchmarks.
With only 3b of parameters, it can also generate large and complex code of over 1000 lines, use tools in a way comparable to large models, and is perfect for agentic tasks.
GRM2 is licensed under Apache 2.0, making it perfect as a FineTune base for other tasks.
OrionLLM/GRM2-3b
Even with only 3b of parameters, it outperforms qwen3-32b in several benchmarks.
With only 3b of parameters, it can also generate large and complex code of over 1000 lines, use tools in a way comparable to large models, and is perfect for agentic tasks.
GRM2 is licensed under Apache 2.0, making it perfect as a FineTune base for other tasks.
OrionLLM/GRM2-3b
- 2 replies