black-forest-labs/FLUX.2-klein-9b-kv
Image-to-Image • Updated • 5.87k • 107
Javed Alam PRO
Javedalam
AI & ML interests
Ai user, tester, and developer of open source ai based applications.
Recent Activity
liked a model 2 days ago
black-forest-labs/FLUX.2-klein-9b-kv liked a model 3 days ago
openbmb/MiniCPM-o-4_5-gguf liked a model 14 days ago
unsloth/Qwen3.5-9B-GGUFOrganizations
liked a
model 2 days ago
liked a
model 3 days ago
liked a
model 14 days ago
liked a
Space 14 days ago
updated a
collection 14 days ago
liked a
model 20 days ago
reactedto OzTianlu's post with 🔥 21 days ago
Post
1723
Scaling UP in Kai! 🌊
NoesisLab/Kai-3B-Instruct
Introducing NoesisLab/Kai-3B-Instruct What happens when you force a 3B model to reason entirely in its latent space ?
Meet Kai-3B, our latest industrial-grade reasoning model fine-tuned using the Adaptive Dual Search (ADS) algorithm.
GSM8K (0-shot, Direct Answer): 39.27% 🤯 (Llama-2-7B is ~14.6%)
HumanEval (Pass@1): 39.02% 💻 (Overtakes Gemma-2-2B's 30%)
MMLU (5-shot): 53.62% 📚 (Crushing the 50% barrier)
ARC-Challenge: 51.88%🎯
PIQA: 77.53%
HellaSwag: 69.53%
Kai-3B proves that reasoning density doesn't strictly require parameter bloat or verbose generation. It acts as a perfect, cold-blooded Agent action-engine—ideal for JSON routing, SWE-bench patch generation, and anywhere you need absolute structured certainty without token waste.
NoesisLab/Kai-3B-Instruct
Introducing NoesisLab/Kai-3B-Instruct What happens when you force a 3B model to reason entirely in its latent space ?
Meet Kai-3B, our latest industrial-grade reasoning model fine-tuned using the Adaptive Dual Search (ADS) algorithm.
GSM8K (0-shot, Direct Answer): 39.27% 🤯 (Llama-2-7B is ~14.6%)
HumanEval (Pass@1): 39.02% 💻 (Overtakes Gemma-2-2B's 30%)
MMLU (5-shot): 53.62% 📚 (Crushing the 50% barrier)
ARC-Challenge: 51.88%🎯
PIQA: 77.53%
HellaSwag: 69.53%
Kai-3B proves that reasoning density doesn't strictly require parameter bloat or verbose generation. It acts as a perfect, cold-blooded Agent action-engine—ideal for JSON routing, SWE-bench patch generation, and anywhere you need absolute structured certainty without token waste.
- 2 replies
published an article 21 days ago
Article
PicoClaw, PicoLM, and the $10-$15 hardware based Edge AI
liked 4
Spaces 22 days ago
LFM2.5 1.2B Thinking WebGPU
💧
91
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Omni Video Factory
🏆
619
text to video, image to video, video extend
Z Image Turbo
🖼
2.59k
Generate high-quality images from text prompts instantly
Wan2.2 14B Preview
🐌
1.38k
generate a video from an image with a text prompt
upvoted a collection 30 days ago
liked a
Space about 1 month ago
updated a
collection about 1 month ago
liked a
model about 1 month ago
updated a
Space about 1 month ago
posted an update about 1 month ago
Post
319
When an AI Model Solves College-Level Math and Physics — On a Phone
This morning I came across a model called Nanbeige4.1-3B, and what began as simple curiosity quickly became something more significant.
I loaded an already 4-bit quantized version and ran it locally on a phone. No GPU, no cloud support, no hidden infrastructure — just a compact reasoning model operating entirely at the edge.
I started with classical mechanics: acceleration, force, friction on an incline. The model worked through them cleanly and correctly. Then I stepped into calculus and gave it a differential equation. It immediately recognized the structure, chose the proper method, carried the mathematics through without confusion, and verified the result.
It did not behave like a model trying to sound intelligent. It behaved like a system trained to solve problems.
And it was doing this on a phone.
For a long time, we have associated serious reasoning in AI with massive models and enormous compute. Capability was supposed to live inside data centers. Bigger models were expected to mean smarter systems.
But watching Nanbeige4.1-3B handle college-level math and physics forces a rethink of that assumption. Intelligence is not only expanding — it is compressing. Better training and sharper reasoning alignment are allowing smaller models to operate far beyond what their size once suggested.
When structured problem-solving runs locally on pocket hardware, the implications are larger than they first appear. Experimentation becomes personal. Engineers can explore ideas without waiting on infrastructure. Students can access serious analytical capability from a device they already carry. Builders are no longer required to send every complex task into the cloud.
What makes moments like this easy to miss is that they rarely arrive with fanfare. There is no dramatic announceme
The model responses are here
https://fate-stingray-0b3.notion.site/AI-model-Nanbeige4-1-3B-304
This morning I came across a model called Nanbeige4.1-3B, and what began as simple curiosity quickly became something more significant.
I loaded an already 4-bit quantized version and ran it locally on a phone. No GPU, no cloud support, no hidden infrastructure — just a compact reasoning model operating entirely at the edge.
I started with classical mechanics: acceleration, force, friction on an incline. The model worked through them cleanly and correctly. Then I stepped into calculus and gave it a differential equation. It immediately recognized the structure, chose the proper method, carried the mathematics through without confusion, and verified the result.
It did not behave like a model trying to sound intelligent. It behaved like a system trained to solve problems.
And it was doing this on a phone.
For a long time, we have associated serious reasoning in AI with massive models and enormous compute. Capability was supposed to live inside data centers. Bigger models were expected to mean smarter systems.
But watching Nanbeige4.1-3B handle college-level math and physics forces a rethink of that assumption. Intelligence is not only expanding — it is compressing. Better training and sharper reasoning alignment are allowing smaller models to operate far beyond what their size once suggested.
When structured problem-solving runs locally on pocket hardware, the implications are larger than they first appear. Experimentation becomes personal. Engineers can explore ideas without waiting on infrastructure. Students can access serious analytical capability from a device they already carry. Builders are no longer required to send every complex task into the cloud.
What makes moments like this easy to miss is that they rarely arrive with fanfare. There is no dramatic announceme
The model responses are here
https://fate-stingray-0b3.notion.site/AI-model-Nanbeige4-1-3B-304
- 4 replies
When an AI Model Solves College-Level Math and Physics — On a Phone
❤️ 7
19
#2 opened about 1 month ago
by Javedalam
liked a
model about 1 month ago
