AI NEWS.ccAI는 지금, 미래는 업데이트 중
♡ 저장한 도구 0
AI 모델 라이브러리/autotrust/JEV-35B-NVFP4
모델 정보

JEV-35B-NVFP4

autotrust · JEV-35B-NVFP4

> [!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. 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 lm_head, 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. * **Text: −0.57 on the Decision Index.** All five areas within 1.2 skill points of bf16 (Knowledge 0.422, Language 0.628, 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. * **Images: −0.85 on the vision rebuild**, a small but real loss (paired bootstrap 95 % interval −1.5 to −0.2), mostly on CharXiv charts (−5.3). * **Robot arm: 13 of 20 scenes against 15 of 20.** Four scenes changed outcome (3 lost, 1 gained), within noise (sign test p = 0.63); every grasped cube still reached the tray (13/13). * **Speed:** the same latency as bf16 on one B200 for single requests; the gain is memory (one 32–48 GB GPU is enough). * **Games** (seed 0, one run each, noisy): 2048 largest tile 64 (bf16 32), Snake 5 food (bf16 11), Quick, Draw! 85.9 % on finished sketches (bf16 86.3 %), chess mate-in-one 45 % (bf16 47 %), Connect Four 1 win of 6 (bf16 0).

번역 대기 중입니다. 원문을 표시합니다.

텍스트 분석license:apache-2.0
컨텍스트 창미공개
입력 → 출력텍스트 → 텍스트
모델 웨이트미확인
정보 업데이트2026/10/29 04:40:06
OVERVIEW

모델 소개

> [!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. 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 lm_head, 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. * **Text: −0.57 on the Decision Index.** All five areas within 1.2 skill points of bf16 (Knowledge 0.422, Language 0.628, 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. * **Images: −0.85 on the vision rebuild**, a small but real loss (paired bootstrap 95 % interval −1.5 to −0.2), mostly on CharXiv charts (−5.3). * **Robot arm: 13 of 20 scenes against 15 of 20.** Four scenes changed outcome (3 lost, 1 gained), within noise (sign test p = 0.63); every grasped cube still reached the tray (13/13). * **Speed:** the same latency as bf16 on one B200 for single requests; the gain is memory (one 32–48 GB GPU is enough). * **Games** (seed 0, one run each, noisy): 2048 largest tile 64 (bf16 32), Snake 5 food (bf16 11), Quick, Draw! 85.9 % on finished sketches (bf16 86.3 %), chess mate-in-one 45 % (bf16 47 %), Connect Four 1 win of 6 (bf16 0).

주요 특징

特点摘要待依据来源补齐，不凭模型名称推断能力。

한계 및 유의 사항

구체적 한계를 판단할 출처가 부족합니다. 실제 성능, 지연, 데이터 정책, 라이선스와 버전 수명을 확인하세요.

PRICING & COST

출처별 요금 및 비용 분석

요금은 채널, 지역, 설정에 따라 다릅니다. 각 채널 요금은 개별 표시되며 제공사의 통일 공식 요금이 아닙니다.

출처 / 채널입력출력과금 단위수집 시간
확인된 요금이 없습니다. 출처를 확인하세요.

월간 기본 토큰 비용 추정

—

추정치에는 캐시 할인, 구간 요금, 멀티모달 추가 요금, 검색, 세금 및 추가 추론 출력이 포함되지 않습니다.

INDEPENDENT BENCHMARKS

공개 평가 및 실행 설정

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

등록된 전체 순위 보기 →

자주 묻는 질문

오픈 웨이트면 무료 상업 이용이 가능한가요?

반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 조건과 정책을 확인하세요. 자체 배포에는 연산 및 유지 비용도 듭니다.

실시간 결제 요금인가요?

수집 시간이 기록된 요금 스냅샷입니다. 최신 버전, 지역, 할인과 과금 방식은 해당 채널에서 확인하세요.

출처 및 추적 기록

huggingface · autotrust/JEV-35B-NVFP4 ↗2026/10/29 04:40:06
huggingface · enrich:e16765bc-0222-4b9a-96de-35ce98473163 ↗2026/10/29 00:18:26

许可证：apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。