gpt-oss-20b-GGUF
Overview
OpenAI's open-weight gpt-oss 20B MoE - capable reasoning and tool use in a 24 GB footprint. A strong mid-tier option.
Recommended hardware
≈ 24 GB VRAM to run this 20B model at the Q6_K quantization.
Fits 24 GB+ consumer GPUs (e.g. RTX 3090, RTX 4090)