llama.
Everything we've published on llama across guides, agents, hardware reviews and glossary entries: 16 entries in total.
Guides (1)
- Local LLM benchmarks on a Pi 5, mini PC, Mac or GPUAI Agents · 2026-10-17
Published llama.cpp speeds for one 7B model on mini PCs, Apple Silicon Macs and Nvidia cards, Raspberry Pi 5 figures, and the memory each model size needs.
Agents (3)
- Nanobot
Personal AI agent in Python (MIT) with a browser UI and chat apps. Native Anthropic, OpenAI and OpenRouter providers plus local servers; its shell sandbox is off until you switch it on.
- NanoClaw
Small TypeScript agent (MIT) built on Anthropic's Claude Agent SDK. Every agent runs in its own Docker container, on macOS, Linux or Windows through WSL2.
- ZeroClaw
Single Rust binary from ZeroClaw Labs, MIT or Apache-2.0. Works with Anthropic, OpenAI, Ollama and about twenty other providers, and turns on an OS sandbox it detects.
Hardware (7)
- Raspberry Pi 5
Raspberry Pi 5 for self-hosted AI: four Cortex-A76 cores, 1 to 16 GB of LPDDR4X. Hosts Hermes Agent (no browser tool) or Nanobot; local models up to about 3B.
- Intel NUC 13 and Geekom IT13
Intel NUC 13 and Geekom IT13: 13th-gen Intel Core mini PCs with 16 to 64 GB of RAM, room for Hermes Agent with browser automation and a 7B model beside it.
- Mac Mini M4 / M4 Pro
Mac mini M4 and M4 Pro for local LLMs: 16 to 64 GB of unified memory at 120 or 273 GB/s, the two specs that decide which models load and how fast.
- Mac Studio M3 Ultra
Apple's 2025 local-LLM workstation: M3 Ultra, 96 GB of unified memory configurable to 256 GB, 819 GB/s. Since replaced by the M5 Ultra model.
- MacBook Air M3 / M4
Fanless laptop with up to 24 GB unified memory. Runs Mistral 7B Q4 silently on the train. €1,299+.
- Lenovo ThinkCentre M75q (used)
Lenovo ThinkCentre M75q, used: a €150-250 Ryzen mini PC with 16 GB of RAM and an NVMe slot, enough for Hermes Agent with the browser tool.
- Minisforum UM790 Pro
Minisforum UM790 Pro: Ryzen 9 7940HS with Radeon 780M graphics and up to 64 GB of DDR5, for a Linux agent host that also runs local models.
Glossary (5)
- Local LLM :A language model running on your own hardware instead of behind a cloud API: Llama, Qwen, Mistral and other open-weight models.
- Ollama :Local LLM runtime that exposes an OpenAI-compatible API over local model weights.
- Llama :Meta's family of open-weight language models, under Meta's own licence.
- llama.cpp :C++ inference engine for LLMs. The runtime under most local-LLM setups, including Ollama.
- GGUF :File format for storing quantised LLM weights, used by llama.cpp and Ollama.