ModelRefs / Best Local LLMs to Run On Your Computer (2026)
Best Local LLMs to Run On Your Computer (2026)
Run LLMs locally with Ollama, llama.cpp or LM Studio. Compare quantised open-weight models, hardware requirements and performance.
Overview
Local LLMs keep prompts and data on-device. Modern quantisation (Q4_K_M, AWQ) lets 7B–13B models run on a laptop, and 70B models on a workstation.
ModelRefs tracks 1 local LLM with a published reference page. Each page states the provider, the capabilities ModelRefs has evidence for, the benchmark results it holds with their dates and sources, and the limitations and coverage gaps that remain.
Models in this category
1 local LLM has a published reference page on ModelRefs.
Listed alphabetically. Category membership means a model is a candidate worth evaluating for this kind of work, not a ranking and not an endorsement — compare the evidence on each page against your own requirements.
Other model categories
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Best Local LLMs to Run On Your Computer (2026).
Frequently asked questions
What hardware do I need to run an LLM locally?
A 7B Q4 model fits in ~6 GB RAM/VRAM. 13B needs ~10 GB, 70B needs ~40 GB. Apple Silicon, modern NVIDIA, and AMD GPUs are all supported.