GraySoft
Model Comparison

city96/wan2.1-t2v-14b-ggufvsmradermacher/gemma-4-31b-cognitive-unshackled-i1-gguf

Side-by-side comparison of city96/wan2.1-t2v-14b-gguf and mradermacher/gemma-4-31b-cognitive-unshackled-i1-gguf: downloads, license, context length, tasks, and benchmarks.

city96/wan2.1-t2v-14b-gguf

city96 · text-to-video

This is a direct GGUF conversion of Wan-AI/Wan2.1-T2V-14B All quants are created from the FP32 base file, though I only uploaded FP16 due to it exceeding the 50GB max file limit and gguf-split loading not currently being supported in ComfyUI-GGUF. The model files can be used wit…

mradermacher/gemma-4-31b-cognitive-unshackled-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/aifeifei798/Gemma-4-31B-Cognitive-Unshackled ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Gemma-4-31B-Cognitiv…

Side-by-side Specifications

city96/wan2.1-t2v-14b-ggufmradermacher/gemma-4-31b-cognitive-unshackled-i1-gguf
Authorcity96mradermacher
Pipeline Tasktext-to-video
Librarygguftransformers
Downloads26,69137,797
Likes1904
LicenseUnknownUnknown
Context Length
Created2025-02-262026-04-06
Last Modified2025-02-262026-04-06
Tags
gguftext-to-videobase_model:Wan-AI/Wan2.1-T2V-14Bbase_model:quantized:Wan-AI/Wan2.1-T2V-14Blicense:apache-2.0region:us
transformersggufroleplaysillytavernidolgooglepytorchDarkIdolgemmagemma4

View full details: city96/wan2.1-t2v-14b-gguf · mradermacher/gemma-4-31b-cognitive-unshackled-i1-gguf