5M+ monthly downloads across AutoTrust AI’s 10 most-downloaded models on @huggingface. Two releases above 1M each. 🚀
Here’s what each model does—and where to start:
1) AutoTrust-Decider-Pro-35B — 1.52M
A single-pass decision model that returns probabilities for up to 256 choices—use it to route support tickets or rank candidate actions.
2) AutoTrust-Decider-Pro-Vision-27B — 1.41M
Makes decisions from text and images, with optional reasoning—use it to interpret charts, select browser actions or experiment with game-control loops.
3) AutoTrust-Decider-Mini-9B — 656K
A compact model for yes/no decisions, multiple-choice selection and ratings—use it to classify requests or score workflow options.
4) AutoTrust-Decider-Pro-27B — 449K
Combines fast probability-based decisions with a separate reasoning mode—use it to assess supplier risks or choose the next step in a workflow.
5) AutoTrust-Decider-Pro-35B-NVFP4 — 395K
The lower-memory Pro-35B variant—run probability-based ticket routing and action selection on a single 32–48GB GPU.
6) GEV-26B-Decide — 248K
A decision model with adaptive thinking—answers straightforward choices directly and calls on reasoning when confidence is low.
7) AutoTrust-Decider-Pro-Vision-27B-v1.1 — 155K
This release handles text-only decisions, with strengths in tool selection and intent classification—use it to match a request to the right tool.
8) GEV-26B-Decide-NVFP4 — 111K
A lower-memory GEV variant for text-and-image decisions—experiment with screenshot-driven browser actions using about 17.1 GiB of GPU weight memory.
9) Qwen3.8-Flash-Next-E384-FP4-V2 — 65.9K
A merged FP4 checkpoint for reasoning, tool calling and structured outputs—test it in self-hosted workflows with the documented B200 setup.
10) Qwen3.8-27B-NVFP4-DGX-SPARK-V2 — 63.5K
A local text-generation model with an optimized speculative-decoding recipe—use your DGX Spark to generate Python code and iterate on coding tasks.
Pick a model that fits your task and hardware. Download it, test it on your own inputs, and follow AutoTrust AI for new releases:
https://t.co/o0WnChacKw
Meet AutoTrust-Decider-Pro-Vision-27B-v1.1: a 27B text-classification powerhouse built on Qwen3.5. It turns messy text into structured decisions, and with 140K+ downloads, the community is already hooked.
140K+ downloads in the past month. Open weights. Measurable gains. 🚀
Thanks @HuggingModels for highlighting AutoTrust AI’s Decider Pro Vision 27B v1.1!
96.25 in tool selection.
97.06 in intent classification.
Sentiment extraction: 27.8 → 55.0, a +27.2-point gain over the starting checkpoint.
Build agents that route requests, select tools, and classify sentiment—with probabilities for each option, rather than free-form answers to parse.
Apache-2.0 weights. Download and test it on your own workflow:
https://t.co/ewtffzNxFb
Reported figures are benchmark skill scores, not accuracy percentages. Local evaluation; pending maintainer verification.
Explore our desktop research workspace—download ScienceGuru:
https://t.co/NH6RP6UykB
Thanks @LysandreJik and the @HuggingModels team for bringing decision models into Transformers—and highlighting AutoTrust AI’s JEV.
Agents don’t always need another generated paragraph. Sometimes they need to choose a tool, rank search results, or select the next action from a screenshot.
JEV’s System 1 path returns calibrated probabilities for explicit options in one forward pass, over text and images. Developers can use those probabilities to set thresholds, route uncertain cases for deeper reasoning, and avoid parsing free-form answers.
A shared model.decide(...) interface means less model-specific glue across inference, training and evaluation. That’s a meaningful step toward making open decision models easier to use.
Download our models and explore the demos:
https://t.co/eXv5y39Dwt
A pretty important new primitive just landed in 🤗 Transformers: **decision models**.
I think this could matter much more than adding support for any single model.
Today, different decision models all approach "making a decision" differently:
- @typesafeai’s Jev, the OG: typed decisions + calibrated probabilities, single forward
- @AutoTrustAI’s JEV builds open System One models around a learned decision block, w/ multimodal.
- @jaredpalmer’s KEV uses a pointer head over the options, sharing the computation of the state across questions.
- @Cloudflare’s CLEF uses a joint schema head that routes evidence between the state, questions and options, scoring the whole schema together.
- @perplexity_ai’s Decider uses a separate 255-way readout on top of Qwen, with non-causal attention in its full-attention layers.
- @liquidai’s d1 is exploring small, multimodal decision models that can run all the way down to the edge.
- And @XunzhuoLiu's Semantic Router team is pushing the serving side hard with System One + the D3 family: one typed interface for choice, score and yes/no decisions, with models from sub-1B to 27B.
That experimentation is good, and needed! But without a common interface, every training framework, inference engine and evaluation tool has to understand every implementation separately.
So Transformers is introducing a shared decision-model layer:
`DecisionConfig`
`pipeline("decision")`
and, most importantly:
`model.decide(...)`
The idea is **not** to make every decision model work the same internally, but for them to speak the same language to the ecosystem around them.
This means that, without running custom or remote code:
- inference engines can serve them through one interface
- training tools can build against common primitives.
- the Hub can package them consistently.
- evaluations can compare them without model-specific glue everywhere.
This is the part of transformers I'm the most excited about: to grow alongside the ecosystem and the many ideas; and to make all of them more usable by everyone.
https://t.co/yslV5Pc8NM
Meet Qwen3.8-Flash-Next-E384-FP4-V2: a new image-text-to-text model with 30k+ downloads and 1.4k likes. It's a MoE model with NVFP4 quantization, built for fast, efficient multimodal understanding. This is the future of accessible AI.
Thanks @HuggingModels for highlighting AutoTrust AI’s Qwen3.8-Flash-Next-E384-FP4-V2!
39K+ downloads in Hugging Face’s rolling monthly window—and a practical direction for Local AI: multimodal reasoning, coding, and tool calling on infrastructure you control.
Our complete, RL-refined FP4 checkpoint reports 95.0% on AIME 2026 and 98.78% on HumanEval.
Building an assistant for private documents, screenshots, and code? Download the model and test it on your own workload:
https://t.co/wldSi2AOod
Which AutoTrust AI decision model should you try first?
JEV-9B — A smaller model combining fast decisions with optional reasoning, a practical starting point for ticket routing and classification.
JEV-27B — Text decisions and full reasoning on one backbone, for workflows that need both option selection and longer explanations.
AutoTrust-JEV-27B-v1.1 — A text-focused decision model with strong evaluated tool-selection and intent-classification results, for choosing which API or workflow to invoke.
JEV-27B-VL — Decisions over text and images, from checking whether a browser agent finished its task to selecting the next move in Mario or Tetris.
GEV-26B-Decide — Fast text-and-image decisions with opt-in adaptive thinking: answer directly when confident, reason further when a logic or math question needs it.
JEV-35B — A sparse MoE model for text-and-image decisions, such as ranking search results or categorizing product listings; it returns decisions, not chat responses.
GEV-26B-Decide-NVFP4 — A lower-memory GEV deployment option for bringing decision workflows onto compatible local hardware.
JEV-35B-NVFP4 — A compressed JEV-35B release with a documented 32–48 GB GPU deployment path, making local ranking and classification more accessible.
JEV-Gemma4-26B-A4B — The earlier Gemma-based release, subsequently published as GEV-26B-Decide with the same weights.
Explore the demos, download a checkpoint, and test it on your own workload:
https://t.co/vtagTOmzNB
Your agent can write an answer. Can it choose the right action?
AutoTrust AI’s Decision Models collection brings together nine open-weight releases, live demos, and public evaluation results — with 5.4M+ combined model downloads in Hugging Face’s rolling monthly window.
Built for decisions you can plug into real workflows:
• A customer reports a duplicate charge. Choose billing, shipping, or technical support — with a probability for each option.
• An agent has several tools available. Select the next tool rather than generate another paragraph.
• A browser agent claims it finished. Evaluate its actions and final screenshot before accepting the result.
• A game presents a new state. Choose the next move — see the Mario and Tetris demos.
Explore JEV-9B, JEV-27B, AutoTrust-JEV-27B-v1.1, JEV-27B-VL, JEV-35B, GEV-26B-Decide, and NVFP4 variants.
From text routing to visual judgments, the family gives developers different model sizes and deployment options for adding a decision layer to their own systems.
Try a demo, download a checkpoint, and test it on decisions your application actually needs to make:
https://t.co/eXv5y39Dwt
Follow @AutoTrustAI for new releases. For a research workspace built by the same team, download ScienceGuru:
https://t.co/NH6RP6UykB
@HuggingModels
Local AI is not one model, one format, or one deployment path.
The AutoTrust AI DGX Spark Models collection brings together six releases optimized for NVIDIA DGX Spark — from GGUF builds for llama.cpp to NVFP4 and MTP-accelerated vLLM deployments.
What can you actually do with them?
Run a local coding assistant against a real repository. Serve a model through an OpenAI-compatible endpoint for an internal tool. Test an agent that can reason, call approved tools, and return results without routing every request through a remote API.
Start with the model that fits your workload:
• GLM-5.3-Flash-GGUF-DGX-Spark for a single-Spark GGUF deployment, with tool calling and reasoning support.
• Qwen3.8-27B-NVFP4-DGX-SPARK for lossless MTP speculative decoding on DGX Spark.
• GLM5.3 Flash E192, E224, and E256 variants for different DGX Spark deployment options.
• GLM-5.3-GGUF-DGX-Spark for the larger GLM 5.3 GGUF route.
The six current releases in the collection have recorded more than 111K downloads over the last month.
Follow the collection for new Local AI releases, choose one model, and test it on a task your team already knows well:
https://t.co/tajIDTFQ1B
Qwen3.8-Flash-Next-E384-FP4-V2 is built for work that needs more than a good chat response.
Imagine an engineering agent handling a real bug ticket: it reads the task, reasons through the likely failure path, calls approved search or test tools, drafts an implementation plan, and returns structured findings for a developer to review.
Or use it for math-heavy coding work: work through an algorithmic problem, produce an implementation, and hand the result back to your existing evaluation or test loop.
This is a full merged FP4 checkpoint after three GRPO-style post-training updates with verifiable rewards. It is a complete model release — not a LoRA adapter — with all weights, tokenizer, configs, and MTP files included.
Reported results under the documented evaluation setup:
• AIME 2026: 95.0
• HumanEval: 98.78
• MMLU: 87.37
• C-Eval: 89.97
• Tool calling: 77.88
For teams building coding agents, reasoning workflows, and tool-using systems, V2 provides a ready-to-serve FP4 checkpoint rather than another adapter to integrate.
Validated with vLLM 0.31 on a single B200. The documented serving path includes FP8 KV cache, prefix caching, reasoning parsing, and Qwen XML tool calling.
Download it, run it on a task your team already knows well, and compare the result in your own harness:
https://t.co/wldSi2AgyF
Qwen3.8-27B-NVFP4-DGX-SPARK-V2 is here. Most Local AI releases stop at quantization. V2 goes further into the inference loop.
It packages the complete Qwen3.8-27B NVFP4 checkpoint with AutoTrust AI’s 64k MTP runtime recipe for vLLM.
The plugin reduces the draft vocabulary from 248,320 to 64,026 rows and quantizes the draft path, while leaving the target model and verification lm_head untouched.
That means less draft-step memory traffic and more practical speculative decoding for local coding, reasoning, tool-driven workflows, and private internal APIs.
Built for Blackwell hardware, including DGX Spark / GB10 and B200. Download it, install the included plugin, and serve it through an OpenAI-compatible vLLM endpoint.
https://t.co/fsw0Vpjtah
Train your decision-model using ms-swift: with model-specific losses, automatic two-level temperature calibration and built-in Open-Jev data.
Also capable of converting causal language models into decision models, with generic_decision option. https://t.co/5PbTr4wM4l
Glad to see @ModelScope2022 bring decision-model training and inference into ms-swift.
AutoTrust AI’s JEV-27B-VL is now included in the framework’s decision workflow via `--task_type decision`, with dedicated loss support, built-in Open-Jev data, and automatic two-level temperature calibration.
This gives developers a more practical route to fine-tune and run calibrated multimodal decisions—where agents need to choose, score, route, or escalate with probabilities they can use.
Explore ms-swift: https://t.co/nNBlyzRqJH
A quick start with ScienceGuru.
Start a chat. Keep your research, code, and data together in one project folder. Customize settings when you need to. Define the goal, materials, and output before work begins. Speak your task, review it, then send.
When it is time to move on, copy a working directory, conversation deeplink, or Markdown and pick up where you left off.
One desktop research workspace for organizing work, defining outcomes, and delivering results.
Download #ScienceGuru: https://t.co/QP4L0pKNc1
New from AutoTrust AI: Qwen3.8-Flash-Next-E384-FP4-Local.
A compact AutoTrust build of NVIDIA’s Qwen3.8 Flash Next FP4 Local checkpoint, designed for practical local deployment.
Our NAS recipe keeps 384 of 512 routed experts in every decoder and MTP layer, while preserving top-10 routing, shared experts, attention, vision tower, and tokenizer.
Result: 79.78 GiB of weights instead of 95.12 GiB — 16.1% smaller.
In our same-harness tests, code, tool use, math, and vision stay close to the original checkpoint. The tradeoff is lower performance on knowledge-heavy multiple-choice tasks, so use the full 512-expert model when that is the priority.
We also include a lossless MTP speculative-decoding recipe for vLLM 0.31: 308.9 tok/s and 3.34× the no-MTP speed on one B200 at greedy decoding.
Explore the model, benchmarks, files, and vLLM setup:
https://t.co/7HKHozV5Wb
After Black October, Bring the AI Home.
A month of critical vulnerabilities, AI-agent campaigns, and ultra-low-cost attacks changed the security calculus.
The answer is not to stop using AI. It is to stop sending your most sensitive data across the internet to rent it.
For source code, regulated records, deal information, and other high-value workflows, ask one question:
Does the data go to the model — or does the model come to the data?
With DGX Spark–class hardware and compressed open models, local AI is now practical. Keep the data, model weights, and agents inside one perimeter.
Read the full argument:
https://t.co/oDAwFahKYg
AutoTrust Decision Models — one collection, from fast local decisions to multimodal agent control.
Every model returns calibrated probabilities for the answer options that matter: route or escalate, pick the next tool, score risk, verify a claim, or decide what action an agent should take next.
Start with the classics:
JEV-9B — compact typed decisions with System 2 reasoning
JEV-27B & JEV-27B v1.1 — our open text decision models
JEV-27B-VL — multimodal decisions across text and images
GEV-26B-Decide — a high-performing general decision model
JEV-35B — larger-scale decision capability
NVFP4 releases — lower-memory deployment options for practical inference
The collection also includes live demos for Mario, Rubik’s Cube, Tetris, and typed decisions, plus the public Decision Index result set.
Together, the models in this collection have now recorded more than 5.4M downloads.
Explore the full AutoTrust Decision Models collection:
https://t.co/eXv5y39Dwt
Want to see what open decision models can actually do?
AutoTrust Spaces is our hands-on demo hub: play Mario, Rubik’s Cube, and Tetris with JEV-27B; test typed decisions with JEV-9B; and explore live News and Shorts demos.
Try the demos:
https://t.co/1M1WCKfT6U
Top 3 in both Vision and Text categories.
Ahead of TypeSafe JEV in Text.
JEV-27B-VL reached No. 1 on Hugging Face Global Trending.
Now AutoTrust-JEV-27B v1.1 is Top 3 on both Jev Decision Index boards.
Text: tied for #3 with a 68.0 Full Score.
That puts our open 27B model ahead of TypeSafe’s hosted Jev 1.13 — and ahead of Liquid AI’s d1-3B — on the same public Decision Index.
Vision: #3 with a 71.9 Full Score, including 74.4 on the public set and 69.3 on the private set.
It ranks ahead of Perplexity Decider v1.2, vLLM-SR d3, and Cloudflare’s clef-omni.
This is not a one-model spike. It is a model family built for the decision layer of agents: structured probabilities for routing, tool selection, claim checks, next-action choice, and escalation to deeper reasoning when confidence is not enough.
AutoTrust is establishing itself as a clear leader in open decision models.
Open weights. Apache-2.0. Built for local deployment.
Explore the Jev Decision Index:
https://t.co/2x0FdWt6cv
Download AutoTrust-JEV-27B v1.1:
https://t.co/8k9qOW8t5X