AutoTrust-Decider-Pro-Vision-27B
autotrustapache-2.0textvision

AutoTrust-Decider-Pro-Vision-27B

Updated Nov 21, 2026
Parameters
27.8B
Context
262,144
License
apache-2.0
Updated
Nov 21, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q5_K_M
2 of 4 quantizations fit AutoTrust-Decider-Pro-Vision-27B with real runtime overhead.
Q4_K_M
16 GB
Q5_K_M
20 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve autotrust/AutoTrust-Decider-Pro-Vision-27B

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

AutoTrust-Decider-Pro-Vision-27B is an open-weight vision-language model published by autotrust on Hugging Face in September 2026, with 27.8B parameters under the apache-2.0 license. It is built on Qwen/Qwen3.8-27B.

Among the 74 vision-language models in this directory it ranks 22nd by monthly Hugging Face downloads, and 29 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 56 GB; 8-bit brings that to ~30 GB and 4-bit (Q4_K_M) to ~16 GB, before activations and any context or image buffers. Even at 4-bit it needs more than 12 GB, so plan on a 24 GB setup. Check exact numbers for your card with the VRAM calculator.

Similar vision-language modelsLink to this section

PopularityLink to this section

AutoTrust-Decider-Pro-Vision-27B was downloaded 893,889 times on Hugging Face in the last month (3,107,691 all-time) and has 5,995 likes.

Run it locallyLink to this section

Weights and usage instructions are on the autotrust/AutoTrust-Decider-Pro-Vision-27B model card; it loads with Hugging Face Transformers.

Local runtimes that fit this model:

  • vllm - high-throughput serving on NVIDIA GPUs
  • transformers - the reference Python library most model cards target

PaperLink to this section

From the community

What users are saying

“JEV-27B-VL is impressive but needs ~80GB VRAM, making it inaccessible to most users. A ~4B variant could run/train on a single 12GB GPU while leaving 2–4GB free for a game or other apps. Proposal: Release JEV-4B-VL, distilled from JEV-27B-VL, preserving the calibrated decision head and System 1/System 2 modes.”

“TypeSafe 托管 API 的协议是 {state, questions: [...]}:多个问题共享一个 state,一次调用返回全部结果。 我想确认模型是否支持(或计划支持)一个 request 提多个共享同一 state 的问题? 如果支持,每个问题回答时是否互相隔离——即决策时看不到其他问题和它们的选项?”

“@Narutoouz Related, though not a JEV build: I built Seb-9B, a smaller (9B) decision model that already runs on Apple silicon through mlx-lm: https://huggingface.co/ironbcc/seb-9b The card's MLX snippet reads the probability of each option key from a single forward pass.”

Frequently asked

Quick answers to common questions

How much VRAM does AutoTrust-Decider-Pro-Vision-27B need?

AutoTrust-Decider-Pro-Vision-27B with 27.8B parameters needs approximately 16 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is AutoTrust-Decider-Pro-Vision-27B better than other autotrust models?

AutoTrust-Decider-Pro-Vision-27B has 27.8B parameters with 262,144 context - a strong choice for vision, long-context.

What license is AutoTrust-Decider-Pro-Vision-27B under?

AutoTrust-Decider-Pro-Vision-27B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs AutoTrust-Decider-Pro-Vision-27B well?

With 27.8B parameters, AutoTrust-Decider-Pro-Vision-27B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for AutoTrust-Decider-Pro-Vision-27B?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~20 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can AutoTrust-Decider-Pro-Vision-27B's context window handle?

AutoTrust-Decider-Pro-Vision-27B supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with AutoTrust-Decider-Pro-Vision-27B?

AutoTrust-Decider-Pro-Vision-27B competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec