yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
Text Generation • 12B • Updated • 187k • 695
Vasyl Dykun
SpyFox
AI & ML interests
Deep learning
Recent Activity
liked a model 1 day ago
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF liked a model 4 days ago
zai-org/GLM-5.2Organizations
liked a
model 1 day ago
liked a
model 4 days ago
upvoted an article 4 days ago
Article
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
ibm-research
• • 36 upvoted an article 16 days ago
Article
Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP
- +3
ariG23498, ror, sergiopaniego, pcuenq, sayakpaul
• • 46 upvoted an article 17 days ago
Article
Introducing North Mini Code: Cohere’s First Model For Developers
CohereLabs
• • 77 upvoted an article 25 days ago
Article
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
ibm-research
• • 88 liked a
model 25 days ago
upvoted 2
articles 25 days ago
Article
Holo3.1: Fast & Local Computer Use Agents
Hcompany
• • 33 Article
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler
- +3
ariG23498, sayakpaul, sergiopaniego, ror, pcuenq
• • 127 liked a
model about 1 month ago
upvoted an article about 1 month ago
Article
Unlocking asynchronicity in continuous batching
- +1
ror, pcuenq, ariG23498
• • 61 upvoted an article about 2 months ago
Article
EMO: Pretraining mixture of experts for emergent modularity
allenai
• • 38 reacted to DedeProGames's post with 🔥 about 2 months ago
Post
8589
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
liked a
Space about 2 months ago
upvoted 3
articles about 2 months ago
Article
How to build scalable web apps with OpenAI's Privacy Filter
- +1
ysharma, freddyaboulton, abidlabs
• • 14 Article
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
nvidia
• • 62 Article
Granite 4.1 LLMs: How They’re Built
ibm-granite
• • 81 liked 2
models about 2 months ago
upvoted an article 2 months ago
Article
Multimodal Embedding & Reranker Models with Sentence Transformers
tomaarsen
• • 62