autotrust/JEV-35B — new model trending #28 on Hugging Face
AutoTrust released JEV-35B, an open-weights 35B Qwen3.5 decision model scoring 59.73 on Decision Index 0.3.
AutoTrust AI published autotrust/JEV-35B, an open-weights System 1 decision model on Qwen3.5-35B-A3B with 35 billion parameters and about 3 billion active per token. On the public Decision Index 0.3 suite it scored 59.73 versus 53.64 for JEV-27B-VL, completing all 140,178 scoreable requests with zero errors, and an approximate vision rebuild scored 71.94. Median latency was 204 ms on one NVIDIA B200. The NVFP4 release is a 25.6 GB download using about 23 GiB of GPU memory and scores 59.18. AutoTrust says the model is not affiliated with TypeSafe AI’s hosted TypeSafe Jev 1.13.
- Mixture-of-experts model: 35B parameters, about 3B active, up to 256 options.
- Decision Index 0.3 public score is 59.73, versus 53.64 for JEV-27B-VL.
- Largest gains include PhishNChips +42.2, HoVer +28.4, and Habermas Machine +28.1.
- NVFP4 build is 25.6 GB and fits a 32–48 GB GPU.
- Independent of TypeSafe AI’s closed TypeSafe Jev 1.13 model.
Full article2,282 words · extracted from huggingface.co · click to collapse
# autotrust/JEV-35B
[](https://news.guru.so/ui)
## 🔴 Live: AutoTrust/GuruSearch recommendation & search demo → [news.guru.so](https://news.guru.so/ui)
> [!IMPORTANT]
> **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a
> calibrated System 1 decision, made in about half a second:
> * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance.
> * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the
> search engines' own order, plus a short answer with citations.
### A System 1 decision model on Qwen3.5-35B-A3B (35 B parameters, about 3 B active per token), up to 256 options in one pass
**Decision Index 0.3, public suite: 59.73** (our scoring with the kit), against 53.64 for
[autotrust/JEV-27B-VL](https://huggingface.co/autotrust/JEV-27B-VL) on the board. Approximate public vision score
**71.94** (our rebuild of the vision benchmarks; JEV-27B-VL 71.67 on the same rebuild, a tie within noise). Median single-request latency
204 ms on one B200 (JEV-27B-VL 271 ms).
> [!TIP]
> **NVFP4 version: [autotrust/JEV-35B-NVFP4](https://huggingface.co/autotrust/JEV-35B-NVFP4)**, the same model with its
> routed experts in NVFP4: **25.6 GB download, 23 GiB of GPU memory** (bf16: 72 GB, 66 GiB), so it runs on one 32–48 GB
> GPU. Decision Index 0.3 public 59.18 (bf16 59.73), vision rebuild 71.23 (bf16 71.94), 96.6 % of the Decision Index
> answers identical to bf16, same latency, same `serve.sh` and API.
| version | download | GPU memory (weights) | Decision Index 0.3 public | vision (rebuild) |
|---|---:|---:|---:|---:|
| [autotrust/JEV-35B](https://huggingface.co/autotrust/JEV-35B) (bf16, this repo) | 72 GB | 66.5 GiB | 59.73 | 71.94 |
| [**autotrust/JEV-35B-NVFP4**](https://huggingface.co/autotrust/JEV-35B-NVFP4) | **25.6 GB** | **23.3 GiB** | 59.18 | 71.23 |
> **Two models, two organisations.** **TypeSafe Jev 1.13** is the hosted, closed model made by TypeSafe AI.
> **autotrust/JEV-35B** is an independent open-weights model built by AutoTrust AI; it is not affiliated with,
> endorsed by, or a product of TypeSafe AI.
## Decision Index 0.3 (public suite)
| | public index |