Best local LLMs by hardware
One recommendation per memory budget, computed from the same index as the calculator — not a list of everything that fits. Pick your capacity; each page names the model for general use, for coding and for images, with the memory maths and what breaks when you ask for more context.
- Best local LLM for 8GB44 models fit; Falcon 3 10B Instruct at GPTQ INT4 (6.1 GB) is the general-purpose pick.9 · RTX 5060 Ti 8G, RTX 5060, RTX 5050…
- Best local LLM for 12GB57 models fit; DeepSeek-V2-Lite Chat at Q4_K_M (10.1 GB) is the general-purpose pick.10 · RTX 5070, RTX 4070 Ti, RTX 4070 Super…
- Best local LLM for 16GB64 models fit; Mistral Small 24B Instruct at AWQ INT4 (13.2 GB) is the general-purpose pick.16 · RTX 5080, RTX 5070 Ti, RTX 5060 Ti 16G…
- Best local LLM for 24GB86 models fit; Seed-OSS 36B Instruct at AWQ INT4 (19.9 GB) is the general-purpose pick.4 · RTX 4090, RTX 3090, Tesla P40 24G…
- Best local LLM for 32GB90 models fit; Nemotron 3.5 Bolt 74B-A9B at IQ2_XXS (23.1 GB) is the general-purpose pick.4 · RTX 5090, Radeon AI PRO R9700 32G, Instinct MI100 32G…
- Best local LLM for Apple silicon88 models fit; Nemotron 3.5 Bolt 74B-A9B at IQ2_XXS (23.1 GB) is the general-purpose pick.24 Apple silicon · Mac M5 Ultra 512G, Mac M5 Ultra 256G, Mac M5 Max 128G…