JEV 35B NVFP4
Text classification model by autotrust
JEV 35B NVFP4 launched on 11 October 2026. It ranked #61 on Daily Launch on 15 October 2026 with a Launch Score of 30, from trending score 218 on Hugging Face. It was new in the ranking that day.
What is JEV 35B NVFP4?
This repository is autotrust/JEV-35B with its 10,240 routed expert MLPs (40 layers × 256 experts) quantized to NVFP4. Everything else is the bf16 model unchanged: attention, linear attention, the shared expert, the routers, the vision tower, the MTP layer, the lmhead, the System 1 adapter, the decision head and the temperatures. Below the NVFP4 comparison, the rest of this card is the JEV-35B card; its tables are the bf16 results unless marked otherwise.
From its model card on Hugging Face
JEV 35B NVFP4 is a model by autotrust on Hugging Face. It is released under the Apache 2.0 license.
How to get JEV 35B NVFP4
Get it from its model card on Hugging Face.
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 30 of 100 on 15 October.