# gpt-oss-120b (MXFP4)

> OpenAI · 116.8B · mxfp4

Canonical: https://gpuninja.com/models/gpt-oss-120b-mxfp4
Data as of: 2026-10-11T15:48:18Z
Path: Home › AI models
- Specs verified: 11 Oct 2026, 15:48 UTC

## Specifications

- Publisher: OpenAI (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:48 UTC)
- Parameters: 116.8B (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Quantization: mxfp4 (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Minimum VRAM: 63.4 GB (Unverified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Context length: 128K tokens (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:40 UTC · checked 11 Oct 2026, 15:48 UTC)
- Modality: text (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:48 UTC)
- License: Apache 2.0 (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:48 UTC)

## Graphics cards that can run it

Board, Chip, VRAM, TDP, Length, Slots, Price, Stock, VRAM headroom

No graphics cards recorded that can run this model.

## Benchmarks

No benchmark results recorded.

## Sources

- https://huggingface.co/openai/gpt-oss-120b — Publisher, Parameters, Modality, License; last verified 11 Oct 2026, 15:48 UTC
- https://huggingface.co/ggml-org/gpt-oss-120b-GGUF/blob/main/gpt-oss-120b-MXFP4.gguf — Quantization, Minimum VRAM; last verified 11 Oct 2026, 15:48 UTC
- https://huggingface.co/openai/gpt-oss-120b/blob/main/config.json — Context length; last verified 11 Oct 2026, 15:48 UTC