← back to catalog · registered 2026-09-26 17:57

kaushikvira/Qwen3.8-27B-swift-abliterated-NVFP4-HF

kaushikvira 27B multimodal second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/kaushikvira%2FQwen3.8-27B-swift-abliterated-NVFP4-HF"
Response includes
  • classification m-uncensored
  • files 11
  • author_summary 3 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-26

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text qwen3.8 nvfp4 w4a4 compressed-tensors vllm sglang blackwell rtx-5090

Related

Total size
17.1 GB
Files
11
Quantizations
1
Registered
2026-09-26 17:57
Last updated on HF
2026-09-26 17:26

Files by quantization

Auxiliary files 11 files 17.2 GB
model.safetensors 16.3 GB ae1b3e07 download
model_mtp.safetensors 810 MB 96b0ece7 download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 183 KB 667ce233 download
recipe.yaml 17.3 KB 46b64a6a download
config.json 12.8 KB 41f9e222 download
chat_template.jinja 8.74 KB c0c686f9 download
README.md 3.25 KB 21521b51 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.10 KB d1a20cc3 download
generation_config.json 257 B c1820ef0 download

README current version from Hugging Face


library_name: transformers
pipeline_tag: image-text-to-text
inference: false
license: apache-2.0
base_model:

  • d0xin/Swift-Qwen3.8-27B-Uncensored-BF16
    tags:
  • qwen3.8
  • nvfp4
  • w4a4
  • compressed-tensors
  • vllm
  • sglang
  • blackwell
  • rtx-5090
  • abliterated
  • uncensored

Swift (1.0) abliterated Qwen3.8-27B NVFP4 (HF format / vLLM-ready)

HF-format quantized weights (compressed-tensors NVFP4, W4A4 group-16) of
d0xin's Swift-Qwen3.8-27B-Uncensored-BF16
(huihui-style abliteration) — this is the exact pre-conversion source of our
NInfer v3 container
Qwen3.8-27B-swift-abliterated-nvfp4full-dflash2-NInfer-v3.

Published for structured-output users: NInfer does not support JSON-schema
output; vLLM does.
DFlash2 speculative decoding is engine-specific and lives
only in the NInfer container.

Sibling: dragooy's Swift-Qwen3.8-27B-abliterated-NVFP4
(a different quantization of the same base — credit to Dragoy for the
HF-format-first idea).

What's inside

  • model.safetensors — 17.1 GiB NVFP4 (W4A4 gs16) text stack + vision tower, W8G32 token embedding + output head; calibrated on 512 Ultrachat samples (seq 2048)
  • model_mtp.safetensors — MTP head (used by the NInfer container; ignored by vLLM)
  • recipe.yaml — the llm-compressor recipe, for reproducibility
  • Packaging note: per-packing-group global scales are unified (shrink-only E4M3 re-encode) — mathematically equivalent to the raw llm-compressor output within E4M3 re-encode precision.

Run with vLLM

pip install -U vllm

vllm serve kaushikvira/Qwen3.8-27B-swift-abliterated-NVFP4-HF \
  --max-model-len 131072     # 32 GB GPU: 131k fits comfortably; 262k on 48 GB+

JSON-schema structured output

from vllm import LLM, SamplingParams
from vllm.sampling_params import GuidedDecodingParams

llm = LLM(model="kaushikvira/Qwen3.8-27B-swift-abliterated-NVFP4-HF", max_model_len=131072)

schema = {
    "type": "object",
    "properties": {"answer": {"type": "string"}, "confidence": {"type": "number"}},
    "required": ["answer"],
}

sp = SamplingParams(temperature=0.0, guided_decoding=GuidedDecodingParams(json=schema))
out = llm.chat([{"role": "user", "content": "What is 2+2? Answer in JSON."}], sp)
print(out[0].outputs[0].text)

Credits & license

  • All model credit to d0xin (uncensored BF16), huihui-ai (abliteration
    lineage), ukisai (Swift post-training), Qwen team (base, Apache-2.0).
  • License: Apache-2.0, inherited through the artifact chain.
  • Quantization/packaging by kaushikvira.

Benchmarks — not measured yet on this packaging

The quantization is identical to our NInfer v3 container of the
same weights (which carries full gate/needle/llama-benchy numbers on a single RTX 5090), but the
vLLM/SGLang-specific numbers for this repo are not measured yet — this is a fresh packaging.

If you run it, please share your numbers in the Community tab (tool + version, GPU, context
length, pp/tg tok/s) — we'll collect them here for everyone.

Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.