license: apache-2.0 base_model:
- huihui-ai/Huihui-Qwen3.6-27B-abliterated
- Qwen/Qwen3.6-27B tags:
- ninfer
- qwen3.6
- abliterated
- vision
- rtx3090 library_name: ninfer
Qwen3.6-27B (Huihui abliterated) — NInfer container v1
Pre-converted .ninfer artifact for Don-Chad/ninfer-3090 / NInfer (container v1, compatible with prebuilt v0.3.1). Includes vision tensors; usable without --text-only on RTX 3090 24 GB.
| Field | Value |
|---|---|
| Filename | qwen3_6_27b_huihui_abliterated.ninfer |
| Size | ~16.29 GiB |
| SHA-256 | 1022d8695caa5d04528f7633e4b21bcbefd3b6173cd67babdd4af0ab682c3dc2 |
| Source BF16 | huihui-ai/Huihui-Qwen3.6-27B-abliterated |
| Converter | upstream tools/convert/qwen3_6_27b (same role-based mixed quant as official NInfer 27B) |
Why this exists
NInfer loads only .ninfer at runtime. This upload skips the large BF16 download + local conversion step.
Quick download
hf download ahmed22xa/Qwen3.6-27B-huihui-abliterated-NInfer `
qwen3_6_27b_huihui_abliterated.ninfer `
--local-dir models
Example CLI (vision OK)
.\ninfer.exe models\qwen3_6_27b_huihui_abliterated.ninfer `
--prompt "Hello" --max-new 64 `
--kv-dtype int8 --mtp-draft-tokens 3 --lm-head-draft `
--no-thinking
Attribution
Abliteration / BF16: Huihui. Base model: Qwen. NInfer format / converter: Neroued / Don-Chad NInfer projects. See linked model cards and the engine repository for licenses.