gpt-oss-20b-GGUF

VRAM needed

≈ 24 GB

Fits 24 GB+ consumer GPUs

Authorunsloth

Parameters20B

QuantizationQ6_K

FormatGGUF

Licenseapache-2.0

File size22.43 GB

Overview

OpenAI's open-weight gpt-oss 20B MoE - capable reasoning and tool use in a 24 GB footprint. A strong mid-tier option.

≈ 24 GB VRAM to run this 20B model at the Q6_K quantization.

Fits 24 GB+ consumer GPUs (e.g. RTX 3090, RTX 4090)