Post
23
Please give a follow to 
OrionLLM
We are conducting extensive research to build the best local models for agentic coding.
We are conducting extensive research to build the best local models for agentic coding.
AI & ML interests
Pretraining, QAT, SLM, Overtraining, AI Interpretability.
Recent Activity
View all activity
Please benchmark and add Kiyo-135M-0960
3
#5 opened about 6 hours ago
by 
DedeProGames
DedeProGames
posted an update about 5 hours ago
Add Kiyo-135M-0960
4
#42 opened about 6 hours ago
by DedeProGames
Please benchmark and add Kiyo-135M-0960
3
#5 opened about 6 hours ago
by DedeProGames
Add Kiyo-135M-0960
4
#42 opened about 6 hours ago
by DedeProGames
Banaxi-Tech
posted an update about 12 hours ago
Post
49
Its Monday. Getting back to working on ACR 1.0.
- 8 replies
Add 11 locally benchmarked models and fix wrapped-label bar alignment
#4 opened about 24 hours ago
by DedeProGames
Add some of my models
17
#3 opened 1 day ago
by DedeProGames
Add 11 locally benchmarked models and fix wrapped-label bar alignment
#4 opened about 24 hours ago
by DedeProGames
Add some of my models
17
#3 opened 1 day ago
by DedeProGames
Banaxi-Tech
updated a
Space 1 day ago
Fully new organization Card!
1
#4 opened 1 day ago
by DedeProGames
Fully new organization Card!
1
#4 opened 1 day ago
by DedeProGames
NanoDex (Alpha): Train decoder-only models in cloud
6
#2 opened 2 days ago
by DedeProGames
Include other SupraLabs models
2
#1 opened 2 days ago
by 
LH-Tech-AI
Banaxi-Tech
posted an update 3 days ago
Post
3011
We're releasing the BananaMind SLM Leaderboard!
It offers a easier look at which models are actually good for your specific needs.
Its primary metric, Intelligence index is a composite of BananaMind Base Bench, PIQA, Hellaswag, ARC Easy and Arithmark 3.
It also allows you to see specific categories like Commonsense on a model.
Check it out at BananaMind/BananaMind-SLM-Leaderboard
It offers a easier look at which models are actually good for your specific needs.
Its primary metric, Intelligence index is a composite of BananaMind Base Bench, PIQA, Hellaswag, ARC Easy and Arithmark 3.
It also allows you to see specific categories like Commonsense on a model.
Check it out at BananaMind/BananaMind-SLM-Leaderboard
- 2 replies
DedeProGames
posted an update 4 days ago
Post
115
🚀 Introducing the GRM-3.2 Family
The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.
GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.
GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.
GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.
All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.
Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf
Organization:
OrionLLM
The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.
GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.
GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.
GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.
All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.
Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf
Organization:
- 2 replies
Banaxi-Tech
posted an update 5 days ago
Post
5574
AGI has arrived.
Just gotta wait for the GLM distill.
Just gotta wait for the GLM distill.
- 29 replies
Banaxi-Tech
posted an update 9 days ago
Banaxi-Tech
posted an update 11 days ago
Post
1942
We're releasing BananaMind Arena.
Its a Huggingface space where you can test out different models and see they're rankings!
Check it out at Banaxi-Tech/BananaMind-Arena
Also please follow @CodeSoft for inspiring me to make it.
Its a Huggingface space where you can test out different models and see they're rankings!
Check it out at Banaxi-Tech/BananaMind-Arena
Also please follow @CodeSoft for inspiring me to make it.