Local-Llm

Alibaba just handed the open-source AI community something remarkable: a model that scores 73.4% on SWE-bench Verified — one of the most demanding real-world software engineering benchmarks — while activating only 3 billion parameters per token during inference. Meet Qwen3.6-35B-A3B, released April 17 under the Apache 2.0 license. The Architecture: Sparse MoE Done Right Qwen3.6-35B-A3B is a Mixture of Experts (MoE) model with 35 billion total parameters, but that number is almost misleading for practical purposes. At inference time, the model activates only 3 billion parameters per token — roughly the compute footprint of a much smaller model, with the knowledge capacity of something far larger. ...

Alibaba’s Qwen3.6-35B-A3B scores 73.4% on SWE-bench Verified and runs on a single 24GB VRAM consumer GPU. Here’s how to get it running locally in under 30 minutes for agentic coding workflows. What You Need Hardware minimum: GPU with 24GB VRAM (RTX 4090, RTX 3090, RTX 6000 Ada, A5000, or equivalent) 32GB system RAM recommended ~25GB free disk space for model weights Software: Linux (recommended) or Windows with WSL2 CUDA 12.1+ drivers installed One of: Ollama, LM Studio, or Python + llama.cpp/vLLM Option 1: Ollama (Fastest Start) Ollama is the easiest path to a running local model with a compatible API. ...

Not every AI workload belongs in the cloud. Liquid AI’s new LocalCowork platform is making a direct bet on that premise — and backing it with a genuinely efficient model architecture that makes local agentic inference practical on consumer hardware. Released March 5, 2026, LocalCowork is an open-source local agentic workflow platform that runs MCP-based agent tasks entirely on-device using Liquid AI’s LFM2-24B-A2B mixture-of-experts model. The headline number: 2 billion active parameters out of 24 billion total. That ratio is what makes local deployment viable. ...

OpenClaw just got its first dedicated hardware product. Nano Labs — a Nasdaq-listed company trading under ticker NA — announced the iPollo ClawPC A1 Mini on March 6, a compact device purpose-built for the OpenClaw AI agent ecosystem. The pitch: run your LLMs locally, use messaging platforms as your primary UI, and eliminate the cloud dependency from your autonomous agent stack. This is a milestone worth paying attention to — not because the product has proven itself yet, but because dedicated agent hardware entering the market signals something real about where the ecosystem is heading. ...

Something significant dropped in the open-source model space today: Alibaba’s Qwen3.5 Small series — a family of four on-device models ranging from 0.8B to 9B parameters — is now publicly available under the Apache 2.0 license. The headline claim from VentureBeat and confirmed by MarkTechPost: the 9B flagship outperforms OpenAI’s gpt-oss-120B on benchmarks, while running on a standard laptop. Let that land for a moment. A 9-billion-parameter model running on consumer hardware beats a 120-billion-parameter cloud model on capability benchmarks. If accurate — and the benchmark citations across multiple independent sources suggest it is — this is a meaningful moment for local and edge agentic deployments. ...