Model-size data for this tier is temporarily unavailable — check back shortly.
Open-weight models that actually fit in 8GB RAM (entry laptops, older MacBook Airs, small VPSes), ranked by intelligence. Memory figures are Q4-quantization estimates with ~30% headroom reserved for the OS and context — every model here runs with Ollama, llama.cpp or LM Studio.
At Q4 quantization a model needs roughly 0.55GB per billion parameters plus overhead, and you should keep ~30% of memory free for the OS and context. That puts the practical ceiling for 8GB RAM around 7B parameters.
Total parameters × ~0.55 bytes (Q4_K quantization, the local-inference default) + ~1.5GB runtime overhead. Lower quantizations (Q2/Q3) shrink further at a quality cost; Q8 or FP16 roughly doubles or quadruples the footprint. Long contexts add KV-cache memory on top.
No — MoE models activate only some experts per token (faster inference), but all weights must stay in memory. A 122B-A10B model needs RAM for all 122B parameters, so these pages size by total parameters.