4-bit AWQ quantization of autotrust/JEV-27B-VL, built with llm-compressor and served with vLLM. System 1 (POST /v1/decide) runs on a single 24 GB GPU — the fp8 build needs two — and on every axis we measured it is faster than the two-GPU fp8 deployment it replaces. The System 1 adapter is merged into the weights (including the decision head), so no --enable-lora is needed. The decision head (lmhead) and the vision tower are kept in bf16; every other text layer is quantized, including the Gated DeltaNet projections of the 48 linear-attention layers — most Qwen3.5-family quants exclude those and therefore do not fit on one 24 GB card. The AWQ step matters: a data-free RTN build of the same…
Organization
AI Outfitters
aioutfitters
Models in Library1
Datasets in Library0
Models on Hugging Face2
Followers1
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image and text to text.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.