NexaAI/gpt-oss-20b-MLX-8bit

Quickstart

Run them directly with nexa-sdk installed In nexa-sdk CLI:

NexaAI/gpt-oss-20b-MLX-8bit

This is a 8-bit quantized version of the OpenAI GPT OSS 20B model.

Original model card: lmstudio-community/gpt-oss-20b-MLX-8bit

Safetensors

Model size

20.9B params

Tensor type

BF16

U32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Quantized

(48)

this model