the AI bench
VERIFIED JUNE 2026
All models

MODEL · OPENAI · 21B TOTAL / 3.6B ACTIVE

gpt-oss-20b

OpenAI's open-weights MoE. Matches o3-mini on common benchmarks, post-trained with MXFP4 quantization so it lands in 16 GB VRAM — a near-frontier reasoner you can actually run on a 5060 Ti.

License: Apache 2.0 · Context: 128K · Released: August 2025

The decision in five lines

The call
Buy — for coding
Best for
coding · chat · agents
Runs on
16 hardware picks fit (cheapest: Minisforum UM890 Pro · $463)
Watch out
When you want a "classic" dense 20B for fine-tuning — MoE fine-tunes are tricky, and the MXFP4 format means not every fine-tuning framework supports it out of the box.
Evidence
Estimated · last verified April 2026

21B total
PARAMETERS
MOE
TYPE
128K
CONTEXT
~16 GB (native MXFP4)
VRAM AT Q4

Where we recommend this

Every tier slot in the planner where this model is a top or alternate pick. Pulled live from planner.js — when the planner refreshes, this table stays current.

CODING · HIGH
gpt-oss-20bOpenAI Apache 2.0; 21B MoE with 3.6B active; near o4-mini on reasoning; fits 16GB.
CODING · MID
gpt-oss-20bMXFP4-native Apache 2.0; fits 16GB cleanly; reasoning + tool use at this tier.
CHAT · MID
gpt-oss-20bOpenAI Apache 2.0 reasoning model; fits 16GB; strong general chat.
AGENTS · HIGH
gpt-oss-20bOpenAI Apache 2.0 reasoning + tool use; 21B MoE fits 16GB.
AGENTS · MID
gpt-oss-20bApache 2.0 reasoning model; strong structured outputs for agents.

The call

OpenAI's open-weights MoE. Matches o3-mini on common benchmarks, post-trained with MXFP4 quantization so it lands in 16 GB VRAM — a near-frontier reasoner you can actually run on a 5060 Ti.

When not to use: When you want a "classic" dense 20B for fine-tuning — MoE fine-tunes are tricky, and the MXFP4 format means not every fine-tuning framework supports it out of the box.

Runner notes

Ollama tag `gpt-oss:20b`. Configurable reasoning effort (low/medium/high) is an in-prompt parameter — see OpenAI's docs for syntax. Drop-in replacement for older Mistral 7B / Qwen 2.5 14B workflows.

License
Apache 2.0
Released
August 2025
Maker
OpenAI

Hardware that fits

Every hardware pick whose memory fits this model at the quant we recommend. Sorted cheapest-first — the top row is your best-value fit. Click through for the full buyer’s guide.

Next step

Find-by-model — see what hardware runs this