ddark-il/Qwen3.8-27B-Uncensored
image-text-to-text model by ddark-il
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A mixed-precision MLX affine quantization of orcarouter/Qwen3.8-27B-Uncensored (27.8 B dense, 64 layers, hybrid GatedDeltaNet + full attention, 256 K context, MTP head, vision tower), built to replicate the recipe of True2456/Qwen3.8-27B-AWQ-5.0bpw and tuned for oMLX on M5 (NAX tensor unit). 17.38 GB · 5.006 bpw · 3.2× smaller than bf16 map and its rationale, the group-size-64 argument for oMLX's NAX prefill path, the no-3-bit constraint (oMLX's qwen35prefill kernels ship q4/q5/q6/q8 only), and the MTP and norm-convention findings. Built on their mlx-compress. Qwen3.8-27B-Uncensored (abliterated fine-tune, revision 11a200330368fd04fa7b2f0b1e7f20bd819cf621). No 3-bit anywhere, and gs64 on everything that can route — gs128 is refused by oMLX's NAX path when the tensor unit is available. reldamp 1e-2, Hessians from real prefill activations of this checkpoint. Measured on the stored bytes: 48/48 attention modules improved, median −32 % H-weighted output error, +31.2 % aggregate. It re-rounds on the grid the export already chose, so only packed…
Read the full model card ↗ · Preview checked 2026-10-29T23:18:21.628Z
Inside the original model card — Document outline
- Qwen3.8-27B-Uncensored — MLX 5.0 bpw (gs64, NAX-first)
- Credits
- Per-module widths
- How this differs from the recipe it replicates
- Running it
- Measured quality
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ddark-il/Qwen3.8-27B-Uncensored is a image-text-to-text model repository published by ddark-il on Hugging Face. The source reports the mlx library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- mlx
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 27,781,427,952
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-25T06:13:39.000Z
- Last modified
- 2026-10-25T06:30:59.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: orcarouter/Qwen3.8-27B-Uncensored
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-25T06:46:38.979Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.