AutoTrust-JEV-27B v1.1 is a text decision model that assigns probabilities to the answer options supplied with each question. This card reports its measured performance on the Decision Index 0.3 public suite. **Public index: 67.31** | **37 indexed benchmarks** | **140,178 completed scoreable requests** This is a complete local evaluation using the official evaluation kit, self-reported pending maintainer verification. No private or Full score is reported.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. > [!IMPORTANT] > **ERQA 56.8% with thinking: above Hy-Embodied-VLM-1.0 with thinking (56.3) and PhysBrain 1.5 (52.8).** No robot or > embodied data in GEV-26B-Decide's decision training (text only); System 2 is the unmodified Gemma-4-26B-A4B-it. > Thinking adds 13.3 points over one pass (43.5% → 56.8%, paired test p (+18.5) and multi-view reasoning (+13.5). **The benchmark.** ERQA (Embodied Reasoning Question Answering) is the benchmark Google DeepMind released with Gemini Robotics (March 2025) to measure whether a vision-language model understands the physical world a robot acts in. It has 400 multiple-choice questions about real robot and everyday scenes, with 1–16 images per question (287 questions have one image). 382 questions have 4 options and the rest 2–3, so chance is about 26%. ERQA is one of the standard embodied-reasoning benchmarks; Gemini Robotics-ER, PhysBrain and Hy-Embodied report it. With 400 questions the 95% interval of a score is about ±5 points.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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/GEV-26B-Decide with its 3,840 routed expert MLPs (30 layers × 128 experts) quantized to NVFP4**. Everything else is the bf16 model unchanged: attention, the dense MLP of every layer, the routers, the vision tower, the lm_head, the System 1 adapter, the decision head and the temperatures. The rest of this card is the card of GEV-26B-Decide; its benchmark tables are the bf16 results, and the NVFP4 comparison is below. GPQA Diamond and HLE are the Decision Index items; the bf16 row is the model's `transformers` engine, the NVFP4 row is vLLM with this checkpoint. The differences are within run-to-run noise (198 questions: about ±7 points).
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. **GLM 5.3 Flash, 12 % smaller — Sparse-Squared compression with AutoTrust SLIM-Q, resident on a single 128 GB DGX Spark with room to spare.** This repository is the llama.cpp GGUF build of the SLIM-Q-compressed GLM 5.3 Flash: 79.1 GiB instead of the stock 90 GiB Q2, with 32 of 288 routed experts removed per layer (256 retained — the **E256** member of the SLIM-Q family) and everything else untouched. It is the single-Spark companion to GLM-5.3-GGUF-DGX-Spark, the 744B SLIM-Q E192 build whose NVFP4 edition powers Guru Turbo 2.0. Runs in llama.cpp (glm5-next), so you get the OpenAI-compatible llama-server, continuous batching, tool calling and `reasoning_content` on the Spark.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. **GLM 5.3 at frontier quality, 24 % smaller — Sparse-Squared compression with AutoTrust SLIM-Q, packaged for DGX Spark owners.** This repository is the llama.cpp GGUF build of **autotrust/GLM-5.3-SLIM-E192**, the SLIM-Q-compressed checkpoint that powers **Guru Turbo 2.0**, served in NVFP4 through **ScienceGuru** and the **Guru Apps**. Here it ships as one 149.7 GiB GGUF (glm-dsa architecture, runs on upstream llama.cpp) sized to fit a pair of DGX Sparks, a single 180 GB GPU, or a Mac Studio.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. **autotrust/GLM5.3-Flash-E192-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for desktop Blackwell systems like NVIDIA DGX Spark. It's an unofficial derivative.** It keeps 192 of the 288 routed experts in each layer by **Neural Architecture Search (NAS)**, uses NVFP4 for the experts and still activates 18 B parameters per token. The weights take 124 GiB, the smallest in the family: **two DGX Sparks connected by ConnectX-7** get about 62 GiB of weights per node and the most KV room of any build, and a single 180 GB Blackwell GPU (B200/GB200) runs it with 32 GiB of KV cache. The KV cache uses FP8.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
> [!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. **autotrust/GLM5.3-Flash-E224-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for desktop Blackwell systems like NVIDIA DGX Spark. It's an unofficial derivative.** > 🚀 **Deploying on DGX Spark?** A complete, field-tested runbook for > serving this checkpoint on **two ConnectX-7-linked DGX Sparks** > (vLLM 0.31.0, TP=2, fp8 KV cache) is here: > **DEPLOY-2X-DGX-SPARK.md** — network setup, > NCCL/CX7 pitfalls, memory budgeting, ops & troubleshooting, and > measured throughput (15.7 tok/s single-stream, 71.8 tok/s at 8-way > concurrency, both GPUs ≈96% utilized).
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
> [!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. **autotrust/GLM5.3-Flash-E256-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for Blackwell systems, from DGX Spark clusters to a single B200. It's an unofficial derivative.** It keeps 256 of the 288 routed experts in each layer by **Neural Architecture Search (NAS)**, uses NVFP4 for the experts and still activates 18 B parameters per token. It's the largest architecture in the family, with the best Chinese, code and vision scores. The KV cache uses FP8.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
> [!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. **autotrust/JEV-27B-VL**, autotrust/JEV-27B with vision, is now online. **Fast, calibrated System 1 decisions that are indistinguishable from the closed TypeSafe Jev 1.13 by KL, and deliberate System 2 generation and reasoning from an untouched Qwen3.8-27B — one set of weights, one vLLM engine, routed per request. It succeeds JEV-9B with closer System 1 fidelity, stronger transfer to unseen tasks and a stronger System 2, and it answers a single decision in about half the time the hosted API takes.**
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. > [!IMPORTANT] > **ERQA 61.5% with thinking (medium): the highest open-model score in the ranking below, tied with Claude Opus 5 and > behind only GPT 6 Astra and Gemini 3.6 Flash.** No robot or embodied data in JEV-27B-VL's decision training (text > only); System 2 is the unmodified Qwen3.8-27B. In one pass (no thinking) it scores 53.8%, above PhysBrain 1.5 (52.8), > the best open embodied model in the report. Thinking adds 7.7 points (paired test p = 0.002). **The benchmark.** ERQA (Embodied Reasoning Question Answering) is the benchmark Google DeepMind released with Gemini Robotics (March 2025) to measure whether a vision-language model understands the physical world a robot acts in. It has 400 multiple-choice questions about real robot and everyday scenes, with 1–16 images per question (287 questions have one image). 382 questions have 4 options and the rest 2–3, so chance is about 26%. ERQA is one of the standard embodied-reasoning benchmarks; Gemini Robotics-ER, PhysBrain and Hy-Embodied report it. With 400 questions the 95% interval of a score is about ±5 points.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. **Decision Index 0.3, public suite: 59.73** (our scoring with the kit), against 53.64 for 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**, 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.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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).
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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. **Fast, calibrated System 1 decisions that are indistinguishable from the closed TypeSafe Jev 1.13 by KL, and deliberate System 2 generation and reasoning from an untouched Qwen3.5-9B — one set of weights, one vLLM engine, routed per request. The fastest model of the family: it answers a single decision in about a third of the time the hosted API takes. Its successor, autotrust/JEV-27B, is closer to Jev, transfers better to unseen tasks and has a stronger System 2.** JEV-9B now takes images. Every step below is **one System 1 decision**: camera image or screenshot in, a probability for every action out, in a single forward pass (about 0.2 s on one GPU). Run it with `bash vl/serve.sh` (see Images: quick start).
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> [!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 bundle serves two systems from one set of base weights. **System 2** is the unmodified `google/gemma-4-26B-A4B-it` (a 26 B-parameter mixture-of-experts model with ≈ 4 B active parameters per token, text and image input): generation and reasoning, bit-identical to the base model. **System 1** adds a LoRA adapter and a 24-slot decision head and returns calibrated probabilities for three typed primitives in one prefill pass: * `noul`: true / false * `choice`: 2–16 options (wider questions are read in groups of ≤ 16 plus a final) * `score`: 0–5
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
A **lossless speed distribution** of `nvidia/Qwen3.8-27B-NVFP4`: the exact same weights, shipped with a fully benchmark-tuned MTP speculative decoding setup. Single-stream decode on a DGX Spark (GB10) goes from **12.5 → 48.2 tok/s (3.9×)**. Screen recording on a DGX Spark: a coding benchmark script streams the model's reasoning and code, then executes the generated program and checks its output (dgx_spark_demo.mov, 4 min 49 s). The same weights and drafter recipe on one NVIDIA B200 (vLLM 0.31.0 OpenAI server, single stream, temperature 0, MTP k=7 — the best setting on B200; k=8 is best on Spark). Four coding tasks: the model streams its thinking and code, then the generated program is executed against tests (all pass). The video is a real-time replay of the measured token arrival times (no speed-up or cuts); token counts include thinking + answer.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
A compact build of nvidia/Qwen3.8-Flash-Next-FP4-Local found by **Neural Architecture Search (NAS)** over the routed-expert configuration: it keeps **384 of the 512 routed experts** in every decoder MoE layer and in the MTP layer. Unchanged from the original: - top-10 routing and the shared experts; - attention, the n-gram PLE table, the vision tower and the tokenizer. **Checkpoint format.** The checkpoint keeps NVIDIA's exact format: - Every kept tensor is a byte-for-byte copy: packed NVFP4 weights, CSF-coded E4M3 block scales, global and input scales, MXFP8 linears and the NVFP4 PLE table. - Only the 49 router matrices change: they keep the rows of the experts chosen by the search. - `text_config.num_experts` is 384.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
