local-ai.net
Run AI on your own hardware.
News, guides, and a catalogue of models, tools, and hardware for local AI. Plus two tools that answer the questions people actually arrive with: what you can run, and whether running it locally is cheaper.
Hardware capability matrix
Tell it your GPU or memory, and see which models fit and at what quantisation. Figures are approximate; fits does not always mean runs well.
Local vs API cost calculator
Work out the break-even point between buying hardware and paying for an API, with the assumptions stated plainly, including the ones that count against local.
Latest news
All news-
6 December 2024
Meta releases Llama 3.3 70B, matching much larger models at lower cost
Meta has released Llama 3.3 70B Instruct, an open-weight model that the company says approaches the quality of its 405B model while needing far less hardware to run. It ships with a 128k context window under the Llama 3.3 Community License.
Featured models
Full catalogue-
Llama 3.3 70B Instruct
Meta · 70B
Meta's 70-billion-parameter instruction-tuned model, delivering performance close to their much larger 405B model at a fraction of the hardware cost. A strong general-purpose choice if you have the VRAM for it.
Permitted with conditions -
Qwen2.5-Coder 7B Instruct
Alibaba · 7B
Alibaba's code-specialised 7B model, strong at code completion and generation well beyond what its size would suggest. A practical choice for a local coding assistant on a mid-range GPU, and permissively licensed.
Commercial use permitted
Learning paths
- Getting Started What local AI is, why it matters, and how to run your first model.
- Hardware GPUs, unified memory, VRAM, and what you actually need for what you want to do.
- Running Models Quantisation, inference engines, model formats, and getting good performance.
- Local AI Coding Code assistants, autocomplete, and agentic coding tools that run on your machine.
- RAG & Knowledge Systems Building retrieval systems over your own documents, entirely locally.
- Agentic AI & Harnesses Tool use, agent frameworks, and orchestration with local models.
- Fine-Tuning Adapting models to your domain: LoRA, QLoRA, full fine-tunes, and when each is worth it.
- Beyond LLMs Image generation, speech recognition, text-to-speech, and other local models.
- Server & Enterprise Running local AI at organisational scale: serving, scaling, and multi-user access.
- Sovereignty & Compliance Data residency, GDPR, the EU AI Act, and the practical case for keeping data in-house.
Local AI is built by people who think running AI on your own hardware matters, for privacy, autonomy, and an open ecosystem. That belief shapes what we cover, not how we report it. We are honest about where local AI falls short and where cloud is the better answer.