MiMo-V2.6 Agentic RL: How Xiaomi Scaled Reinforcement Learning Across Billions of Tokens
25 days ago 高效码农MiMo-V2.6 Technical Report, Explained: What Scaling Agentic Reinforcement Learning Actually Takes Xiaomi’s LLM-Core team set out to answer a narrow question in this report: if you scale reinforcement learning along three axes at once, compute, environment diversity, and grader compute, does model capability keep climbing? The answer is yes. DeepSWE jumped from 19.0 in the previous generation to 71.9, CyberGym from 40.0 to 94.0, and the team open-sourced the training dynamics, RL environments, and end-to-end framework behind those numbers. The report runs over forty pages and covers architecture, pre-training, mid-training, RL, infrastructure, and open reproduction. This walkthrough reorders the material …
I Ran a 2.78 Trillion Parameter Kimi K3 LLM on 8GB RAM with No GPU: Here’s How It Actually Works
1 months ago 高效码农I Ran a 2.78 Trillion Parameter LLM on 8GB RAM with No GPU: Kimi K3 in C The short version, upfront: This isn’t marketing fluff about “running a 2.78T model in 8GB.” I actually ran the inference engine on a standard laptop with only 8 GB of RAM, got the correct first token, and verified that it produces byte-for-byte identical outputs compared to a 224 GB server rack. The catch? Each token takes about half a minute. This post is a hands-on log of setting it up—downloading the 1.56 TB checkpoint, packing the trunk, running the same prompts across different …
Trinity Large AI Model Deep Dive: The 400B Sparse MoE Powerhouse Explained
8 months ago 高效码农Trinity Large: A Deep Dive into the Open-Source 400B Sparse Mixture-of-Experts Model January 29, 2026 In the rapidly evolving landscape of artificial intelligence, the development of large language models continues to push boundaries. Today, we explore Trinity Large—an innovative open-source model that represents a significant advancement in efficient, high-performance AI. This comprehensive analysis covers its unique architecture, training methodology, performance benchmarks, and practical applications. Understanding Trinity Large’s Architecture Trinity Large stands as a remarkable achievement in model design: a 400 billion parameter sparse Mixture-of-Experts (MoE) architecture with only 13 billion active parameters per token. This sophisticated approach utilizes 256 experts …
The A.X K1 Deep Dive: A 519B MoE Model with Think-Fusion Intelligence
9 months ago 高效码农Deep Dive into A.X K1: Architecture Design and Think-Fusion Evolution of a 519B MoE Model Snippet: A.X K1 is a 519B-parameter Mixture-of-Experts (MoE) model by SK Telecom, activating only 33B parameters for efficient inference. It introduces the Think-Fusion training recipe, enabling a unified model to switch between high-speed “intuition” and deep “reasoning” modes, setting new benchmarks in Korean and multi-language AI performance. In the pursuit of Artificial General Intelligence (AGI), the industry faces a constant tug-of-war: how to maintain massive model capacity without skyrocketing inference costs. The newly released A.X K1 technical report provides a definitive answer. By leveraging a …
NVIDIA Nemotron-3-Nano Architecture: How the 31B MoE Model with Mamba-2 Delivers 1M Context
10 months ago 高效码农Nemotron-3-Nano Under the Hood: 31 B Parameters, 3 B Active, 1 M Context, 3× Faster Inference “ TL;DR: NVIDIA’s latest open-weight model keeps 128 experts on standby, wakes up only 6, and mixes Mamba-2 with Group-Query Attention to deliver 25 T token pre-training, multi-environment RL, and FP8 inference that outruns models twice its activated size while supporting 1 M token context. What Makes Nemotron-3-Nano Special in One Sentence? It achieves higher accuracy than Nemotron-2-Nano and competitive models while activating less than half the parameters per forward pass and delivering up to 3.3× higher inference throughput on a single H200 GPU. …
Running an 8.3 B-Parameter Neural Network on a Phone CPU: Inside LFM2-8B-A1B’s Sparse-Magic and On-Device Deployment Guide
1 years ago 高效码农“ “Mixture-of-Experts only lives in the cloud?” Liquid AI just proved that idea wrong with a Samsung Galaxy S24 Ultra and a 2-second local reply. 1. Opening scene – why this model matters It is 1 a.m. and you are still polishing a slide deck. A pop-up asks: “Summarise this 200-page English PDF into ten Chinese bullets, please.” Old routine: copy → cloud assistant → wait → pay. New routine: press “Run” on your phone; two seconds later the answer is there – no Internet, no fee, no data leakage. The engine behind the new routine is LFM2-8B-A1B, Liquid AI’s …