Independent publisher
Blah Blah
blaj
openvino, sub 32gb ram workflows
Compare the published evidence
This profile connects the 6 model and dataset records 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, Text to image.
Reported licenses: apache-2.0, other. 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.
Models
The DFlash speculative-decoding draft for heretic-org/Qwen3.8-27B-heretic-ara, converted to OpenVINO IR at int8 so it can be paired with an OpenVINO target in OVMS or OpenVINO GenAI. Not a standalone model. It consumes the target's intermediate hidden states and proposes candidate tokens; the target verifies them. hiddenstates carries the 5 layers named by dflashconfig.targetlayerids (1,16,31,46,61), concatenated on the last axis. The target must export hiddenstatesdecoderlayers RT-info; the Optimum Intel export carries it automatically. OVMS logs Draft model strategy: DFlash when the pairing is accepted. Exported with Optimum Intel (text-generation-with-past, --trust-remote-code…
The DFlash speculative-decoding draft for heretic-org/Qwen3.8-27B-heretic-ara, converted to OpenVINO IR at fp16 so it can be paired with an OpenVINO target in OVMS or OpenVINO GenAI. Not a standalone model. It consumes the target's intermediate hidden states and proposes candidate tokens; the target verifies them. hiddenstates carries the 5 layers named by dflashconfig.targetlayerids (1,16,31,46,61), concatenated on the last axis. The target must export hiddenstatesdecoderlayers RT-info; the Optimum Intel export carries it automatically. OVMS logs Draft model strategy: DFlash when the pairing is accepted. Exported with Optimum Intel (text-generation-with-past, --trust-remote-code…
The DFlash speculative-decoding draft for heretic-org/Qwen3.8-27B-heretic-ara, converted to OpenVINO IR at int4 so it can be paired with an OpenVINO target in OVMS or OpenVINO GenAI. Not a standalone model. It consumes the target's intermediate hidden states and proposes candidate tokens; the target verifies them. hiddenstates carries the 5 layers named by dflashconfig.targetlayerids (1,16,31,46,61), concatenated on the last axis. The target must export hiddenstatesdecoderlayers RT-info; the Optimum Intel export carries it automatically. OVMS logs Draft model strategy: DFlash when the pairing is accepted. Exported with Optimum Intel (text-generation-with-past, --trust-remote-code…
converted to OpenVINO IR with weights compressed to INT8 by NNCF. A 27B qwen35 vision-language model: 64 text layers (48 linear-attention, 16 full-attention), hidden 5120, plus a 27-depth vision tower. nncf.compressweights with: - mode: INT8ASYM - bits: 8 Ships openvinomtpmodel., the multi-token-prediction head exported by Optimum Intel. Pair with a matching DFlash draft for block-parallel speculative decoding. Optimum Intel (image-text-to-text), Transformers 5.2.0, OpenVINO 2026.3.1. Note: the export requires TMPDIR on a real disk. /tmp is a 16 GB tmpfs and OpenVINO stages the compressed weights there; this export stages ~74 GB, so keep that much free on the TMPDIR filesystem. Apache-2.0.…
OpenVINO IR build of Qwen-Image-2.1 with an abliterated text encoder, quantized to INT4. Runs text-to-image on Intel Arc iGPUs. Uncensoring lives in the prompt-embedding path, so only the Qwen3-VL text encoder needed replacing — the transformer, VAE and vision encoder are the stock model. Total ~13 GB. Embeddings for "a portrait of a woman, photorealistic" differ decisively from the stock encoder — this is not a renamed copy: Intel Core Ultra 7 258V, Arc 130V/140V iGPU, 8 cores, 30 GB RAM: Requires the nightly stack: diffusers and optimum-intel from main, plus OpenVINO 2026.5.0 nightly. See the full conversion write-up…