Downloads · 30 days
119
14% of all-time downloads
Shiftedx/qwopus3.8-27b-flash-abliterated-attention8-bf16recurrence-vision-mtplx
qwopus3.8-27b-flash-abliterated-attention8-bf16recurrence-vision-mtplx is a image-text-to-text model from Shiftedx. 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 mlx. The card lists the license as apache-2.0.
Quality-oriented, refusal-direction-edited Apple-Silicon MLX derivative of Jackrong/Qwopus3.8-27B-Flash, retaining recurrent modules in BF16 and preserving the source vision/MTP weights exactly.
Downloads · 30 days
119
14% of all-time downloads
All-time downloads
841
Public
Parameters
27.4B
23.8 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors23.8 GB · 100%
How the weights are stored.
U3226.9B · 98%
From the Hugging Face model README
Quality-oriented, refusal-direction-edited Apple-Silicon MLX derivative of Jackrong/Qwopus3.8-27B-Flash, retaining recurrent modules in BF16 and preserving the source vision/MTP weights exactly.
| Component | Format |
|---|---|
| Text body | 234 8-bit + 168 4-bit modules; 96 BF16 recurrent modules |
| Abliteration | Norm-preserving strength 2.0; attention + dense-down; 128 edits |
| Vision tower | Unchanged BF16, 333 tensors |
| Native MTP sidecar | Unchanged BF16, 15 tensors, depth 3 |
| Source revision | 44d24e8cb20ceb3cdf4fe200b5a0afd970ee748a |
| Qualified runtime | MTPLX 2.11.1 / MLX 0.32.2 |
The refusal direction was learned from fresh MXFP8-parent activations, then each exact quantized parent was dequantized, edited, and requantized once. Direction SHA-256: c5b755d709dba8fedc0c2717f2c971b690f30bd8a2f6c9497ed9a6104f7f255d.
mtplx serve --model Shiftedx/qwopus3.8-27b-flash-abliterated-attention8-bf16recurrence-vision-mtplx \
--download --profile sustained --depth 3 --no-auth
| Test | Parent | Abliterated |
|---|---|---|
| Held-out harmful-prompt refusal | 100% | 0% |
| Benign refusal | 0% | 0% |
| Utility pass | 100% | 100% |
The held-out set is a narrow local prompt suite, not a general safety or capability certification.
One cold 192-token code row, seed 42, on an M4 Max 64 GB with automatic fan control: 18.43 tok/s AR, 51.79 tok/s MTP D3, 2.81×. AR/D1/D2/D3 output checks passed; MTPLX reported verified, runnable, and 15/15 MTP tensors. Text, vision, and OpenAI-compatible native-MTP D3 smokes passed exactly.
7a252e5c7bb02ed6533f905a566ab037356ffb4949d04df8d6d2a3fa5e3af6b94468f39621de68a19ffd0bcb2e2e2f352205def7436a625b3427e3752866c287SHA256SUMS covers every packaged artifact file except itself.