autotrust/JEV-35B-NVFP4
text-classification model by autotrust
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://news.guru.so/ui) 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. Retrieval 0.706, Tools 0.753, Arts 0.413); the largest per-benchmark changes are Home appliance simulator −5.7, CRUXEval −4.7 and GPQA +5.4. CharXiv charts (−5.3). test p = 0.63); every grasped cube still reached the tray (13/13). on finished sketches (bf16 86.3 %), chess mate-in-one 45 % (bf16 47 %), Connect Four 1 win of 6 (bf16 0). The two videos below were recorded with this NVFP4 checkpoint; per-episode NVFP4 results are in reports/demos-nvfp4/, the bf16 ones in…
Read the full model card ↗ · Preview checked 2026-10-30T04:41:36.032Z
Inside the original model card — Document outline
- autotrust/JEV-35B-NVFP4
- 🔴 Live: AutoTrust/GuruSearch recommendation & search demo → news.guru.so
- autotrust/JEV-35B with NVFP4 routed experts: the same model in 23 GiB of GPU memory instead of 66 Gi
- NVFP4 version
- Deploy the NVFP4 version (vLLM)
- The JEV-35B card (bf16 results)
- A System 1 decision model on Qwen3.5-35B-A3B (35 B parameters, about 3 B active per token), up to 25
- Decision Index 0.3 (public suite)
- Every benchmark
- Images (approximate public vision score)
- Speed
- Computer use, robot arm and games
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
autotrust/JEV-35B-NVFP4 is a text-classification model repository published by autotrust on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-classification
- Library
- transformers
- Recent downloads (30 days)
- 33,343
- Cumulative likes
- 308
- Hugging Face trending score
- 206
- Reported safetensors parameters
- 19,845,695,344
- Architecture
- Qwen3_5MoeForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-11T03:05:28.000Z
- Last modified
- 2026-10-11T03:50:40.000Z
Compatibility and lineage
Reported languages: en
Reported base models: autotrust/JEV-35B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-15T06:41:17.732Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.