Downloads · 30 days
16
22% of all-time downloads
matthid/Ektome-Qwen3.8-27B-PristinelyUncensored-EXL3-SC4-H5-V6
Ektome-Qwen3.8-27B-PristinelyUncensored-EXL3-SC4-H5-V6 is a image-text-to-text model from matthid. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for exllamav3. The card lists the license as apache-2.0.
An EXL3 conversion of Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored, made from source revision f2d5a063b297835e1c32c87712245802c9d9c9c1. It retains the model's vision tower and native MTP head.
Downloads · 30 days
16
22% of all-time downloads
All-time downloads
73
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
How the weights are stored.
I166.8B · 83%
From the Hugging Face model README
An EXL3 conversion of
Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored,
made from source revision f2d5a063b297835e1c32c87712245802c9d9c9c1.
It retains the model's vision tower and native MTP head.
This is a quantized derivative, not a new fine-tune. Please read the source model card for its intended behavior and limitations. The source and this conversion are distributed under Apache-2.0; attribution belongs to the original model authors and the Ektome publisher.
| Component | Format |
|---|---|
| Decoder | self-calibrated EXL3, target 4.0 bpw |
| Decoder allocation | 34 tensors at 3-bit, 297 at 4-bit, 65 at 5-bit, 4 at 6-bit |
| Output head | 5-bit |
| MTP | 4-bit |
| Vision tower | 6-bit |
The decoder allocation was recovered from turboderp's stock-Qwen
SC_4.00bpw_H5_V6 manifest and applied to the architecture-identical Ektome
weights. Calibration used an audited, retokenized 250 x 2048 trace containing
no private user sessions. The artifact is approximately 16 GiB.
109629b78bd6a1c04e2a4ba8f7702efa9c99e84aThe included portable scripts install those pinned core runtime versions on 64-bit Linux with Python 3.12 and an NVIDIA driver compatible with CUDA 12.8. They bind only to localhost and enable API authentication by default.
# Requires Git LFS and Hugging Face authentication while this repo is private.
git lfs install
git clone https://huggingface.co/matthid/Ektome-Qwen3.8-27B-PristinelyUncensored-EXL3-SC4-H5-V6
cd Ektome-Qwen3.8-27B-PristinelyUncensored-EXL3-SC4-H5-V6
bash scripts/install-runtime.sh
bash scripts/serve.sh
The repository checkout itself is the model directory. serve.sh prints the
location of a locally generated API key, then serves
an OpenAI-compatible API at http://127.0.0.1:8000/v1. Override, for example,
with PORT=8080 CTX_SIZE=131072 bash scripts/serve.sh. Do not expose the service
to a network without applying your own firewall, TLS, and secret-management
policy. The pinned upstream TabbyAPI prints API credentials on startup; treat
its terminal output and logs as secrets. These are local serving keys, not your
Hugging Face token.
Results below are from one RTX 3090 and the pinned runtime, so they are not guarantees for other hardware, prompts, drivers, or runtime versions.
Long-context memory and speed are workload-sensitive. Start with 131072 or a smaller window if your GPU or workload differs.
response_format.type=json_object support in the tested TabbyAPI revision
uses the small compatibility patch included under patches/.Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensoredturboderp/Qwen3.8-27B-exl3, branch
SC_4.00bpw_H5_V6, revision
516bf129059031c6da9416768ea6b7a1be00a8fcSee CONVERSION.lock, conversion/README.md,
the recovered recipe and exact converter input under calibration/. Verify the
download with sha256sum -c SHA256SUMS. Model files are unchanged from the tested
build; this model card and portable setup scripts were added for publication.
The scripts passed shell/YAML checks but have not been exercised in a fresh
installation; the measurements are from the original deployment, not these wrappers.
This model inherits the source model's reduced refusal behavior. That is not a guarantee of correctness or safe outputs; apply application-appropriate controls. Base model credit: Qwen/Qwen3.8-27B.