For latency purposes on edge devices, we wanted it to be a non-thinking model. That was a big challenge, but we managed to squeeze a ton of performance from LFM2-1.2B and perform on par with much bigger models on our internal bench (see figure) but also BFCL v3 and v4.
LLMS
-

RAG Model Excels at Long Context Processing and Information Retrieval
By
–
We also have a RAG model It's particularly good for processing long contexts and retrieving relevant information. It's very flexible and can adapt to various input styles.
-

350M Model Shows Power of Fine-Tuning for Big Data
By
–
It comes in two sizes: 1.2B and 350M I'm a big fan of the 350M model that can be used on GPUs to do big data operations. It's an absolute banger that shows how powerful fine-tuning can be
-

Tiny Task-Specific AI Models for Edge Devices
By
–
We're releasing a collection of tiny task-specific models Want to do data extraction, translation, RAG, tool use, or math on a Raspberry Pi? We got you covered! Here are a few examples ↓
-
Using XML to improve Claude model performance
By
–
XML is a great way to get best results from Claude
-
100+ Free Step-by-Step AI Agents and RAG Tutorials
By
–
100+ free step-by-step tutorials with code covering: AI Agents RAG Systems Voice AI Agents MCP AI Agents Multi-agent Teams Autonomous Game Playing Agents P.S: Don't forget to subscribe for FREE to access future tutorials.
-
Nemotron: Building Open Source AI for GPU Systems
By
–
“There's two reasons why we're building Nemotron. The first is because it helps us build the GPUs and systems for the future.”
— NVIDIA (@nvidia) 25 septembre 2025
The second reason is because trust is the foundation of impactful AI–and it starts with understanding. That’s why Nemotron was built open source at its… pic.twitter.com/H1ih4x1WBi“There's two reasons why we're building Nemotron. The first is because it helps us build the GPUs and systems for the future.” The second reason is because trust is the foundation of impactful AI–and it starts with understanding. That’s why Nemotron was built open source at its
-

Budget GPU Setup Enables Cheap Local Private AI
By
–
we've got an Intel Arc GPU in the house – 2015 build -> ~$250 USD
– Intel Arc A770, 16GB VRAM -> $200 USD
– some tinkering
– local and private AI that you control, for cheap love this kind of effort
the DeepSeek way of making it work -
Meta FAIR Introduces Code World Model for Advanced Code Generation Research
By
–
New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code.
— AI at Meta (@AIatMeta) 24 septembre 2025
We believe in advancing research in world modeling and are sharing CWM under a research license to help empower… pic.twitter.com/kwykTJu1GFNew from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower
-

Qwen3-Coder Plus API Upgraded with Enhanced Features
By
–
Qwen3-Coder upgraded! New Qwen3-coder-plus API on @alibaba_cloud Model Studio: Better terminal tasks (aces Terminal Bench) SWE-Bench score hits 69.6 Safer code generation
Qwen Code now supports images & sub-agents!
#Chat #API #Code #AI #Coding @Alibaba_Qwen
