GraySoft
Download guIDE →
Model Comparison

lmstudio-community/nvidia-nemotron-3-super-120b-a12b-ggufvsunsloth/glm-4.6v-flash-gguf

Side-by-side comparison of lmstudio-community/nvidia-nemotron-3-super-120b-a12b-gguf and unsloth/glm-4.6v-flash-gguf: downloads, license, context length, tasks, and benchmarks.

lmstudio-community/nvidia-nemotron-3-super-120b-a12b-gguf

lmstudio-community · —

unsloth/glm-4.6v-flash-gguf

unsloth · image-text-to-text

This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

Side-by-side Specifications

lmstudio-community/nvidia-nemotron-3-super-120b-a12b-ggufunsloth/glm-4.6v-flash-gguf
Authorlmstudio-communityunsloth
Pipeline Task—image-text-to-text
Library—transformers
Downloads29,50619,351
Likes8100
LicenseUnknownUnknown
Context Length——
Created2026-03-102025-12-09
Last Modified2026-03-112025-12-27
Tags
ggufbase_model:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16base_model:quantized:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16license:otherendpoints_compatibleregion:usconversational
transformersggufunslothimage-text-to-textzhenarxiv:2507.01006base_model:zai-org/GLM-4.6V-Flashbase_model:quantized:zai-org/GLM-4.6V-Flashlicense:mit

View full details: lmstudio-community/nvidia-nemotron-3-super-120b-a12b-gguf · unsloth/glm-4.6v-flash-gguf