Nemotron 3 Ultra (free)
NVIDIA · Jun 4, 2026
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts…
GLM 5.3 Flash NVFP4 is a image-text-to-text model published on Hugging Face by nvidia.
nvidia/GLM-5.3-Flash-NVFP4GLM 5.3 Flash NVFP4 is an open-weight model from NVIDIA, released on Sep 2, 2026, with the mit license, 6,045 Hugging Face downloads in the last 30 days.
Specs are sourced from Hugging Face and were last checked on Sep 12, 2026. Always confirm current pricing and limits with the provider before production use.
GLM 5.3 Flash NVFP4 was published on Sep 2, 2026.
GLM 5.3 Flash NVFP4 is published as an open-weight model on Hugging Face under the mit license, so you can download the weights and run them on compatible hardware, subject to the license terms.