← back to catalog · registered 2026-09-19 00:56

d0xin/Swift-Qwen3.8-27B-Uncensored-NVFP4-LocalHessian-ActivationHeadroom-NInfer

d0xin 27B multimodal second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/d0xin%2FSwift-Qwen3.8-27B-Uncensored-NVFP4-LocalHessian-ActivationHeadroom-NInfer"
Response includes
  • classification m-uncensored
  • files 10
  • 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
1
Model age
today
created 2026-09-19

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
other
Tags
ninfer qwen3.8 swift uncensored nvfp4 fp8 mixed-precision local-hessian activation-headroom dflash2 vision multimodal

Related

Total size
0 B
Files
10
Quantizations
1
Registered
2026-09-19 00:56
Last updated on HF
2026-09-19 01:24

Files by quantization

Auxiliary files 10 files 22.1 GB
Swift-Qwen3.8-27B-Uncensored-NVFP4-LH-ActHeadroom.ninfer 22.1 GB a298e285 download
LICENSE 13.0 KB adfde1bf download
LICENSE-APACHE-2.0 11.3 KB f938136e download
README.md 7.51 KB 75ed6ac5 download
BENCHMARKS.json 1.74 KB d9716932 download
.gitattributes 1.57 KB b76ea97c download
QUANTIZATION.json 1.36 KB b8316ac1 download
NOTICE 1016 B d2e5825a download
RELEASE_VALIDATION.json 862 B 2d5b0fe3 download
SHA256SUMS 687 B 791f55e8 download

README current version from Hugging Face


license: other
license_name: swift-open-license-1.0
license_link: https://huggingface.co/ukisai/Swift-Qwen3.8-27b/blob/main/LICENSE
library_name: ninfer
pipeline_tag: image-text-to-text
inference: false
base_model: d0xin/Swift-Qwen3.8-27B-Uncensored-BF16
base_model_relation: quantized
tags:

  • qwen3.8
  • swift
  • uncensored
  • nvfp4
  • fp8
  • mixed-precision
  • local-hessian
  • activation-headroom
  • ninfer
  • dflash2
  • vision
  • multimodal
  • blackwell
  • sm_120a
  • not-for-all-audiences

Swift-Qwen3.8-27B-Uncensored-NVFP4-LocalHessian-ActivationHeadroom-NInfer

Native NInfer build of d0xin/Swift-Qwen3.8-27B-Uncensored-BF16, re-quantized from BF16 using NVIDIA ModelOpt Local-Hessian calibration + activation headroom and a conservative mixed NVFP4/FP8 topology.

Release goals

The goal of this release is straightforward: retain Swift-Qwen3.8's
capabilities while removing refusal behavior.

It is designed to preserve Swift-Qwen3.8's reasoning, agentic, tool-calling,
multimodal and long-context capabilities while removing refusal behavior.

For this quantized build specifically, the goal is also to increase inference
throughput and reduce VRAM usage while preserving FP8-level measured quality
and avoiding longer reasoning traces under the recommended B2048 serving
profile.

In our fixed validation, this build delivered +20–27% decode throughput,
+34–38% prefill throughput, and 15.1% lower VRAM usage
versus FP8, while
scoring 225/280 vs 224/280 on the B2048 MMLU-Pro subset. Mean reasoning
usage was also lower: 741.9 vs 793.0 tokens.

What makes this build different

This is not a repack of an existing NVFP4 checkpoint.

Component Precision
MLP layers 0-55 NVFP4 W4A4
MLP layers 56-63 row-wise FP8
Self-attention projections row-wise FP8
Linear-attention / GDN projections row-wise FP8
GDN a/b BF16
LM head row-wise FP8
Embedding row-wise FP8

Calibration used NVIDIA ModelOpt Local-Hessian, activation headroom, FP8 scale sweep, layer-wise checkpointing, upper_percentile=99.99, and rho=16384.

Quality validation

Fixed MMLU-Pro subset: 280 questions, 14 categories, 20 questions per category, seed 20260918, temperature=0, reasoning_effort=xhigh, max_tokens=4096.

Build Correct Accuracy
FP8 211/280 75.36%
NVFP4 Headroom 207/280 73.93%
FP8 + B2048 224/280 80.00%
NVFP4 Headroom + B2048 225/280 80.36%

For FP8+B2048 vs this build+B2048: both correct 216, both wrong 47, FP8-only correct 8, NVFP4-only correct 9, exact McNemar p=1.0.

No statistically significant accuracy difference was observed on this subset.

Recommended thinking budget

Recommended NInfer setting: --default-thinking-budget 2048.

Without a thinking budget, 36/280 NVFP4 evaluation generations reached the 4096-token output ceiling. With B2048, reasoning median was 379.5 tokens, p90 was 2072, mean was 741.87, 0/280 reached the 4096-token limit, all 280 requests finished normally, and accuracy was 225/280.

The thinking budget is a serving recommendation and is not baked into the artifact.

Performance vs FP8

Test hardware: NVIDIA RTX PRO 6000 Blackwell Workstation Edition.

Metric FP8 This build Change
Decode C1 134.87 tok/s 162.32 tok/s +20.4%
Decode C8 87.33 tok/s 110.58 tok/s +26.6%
Prefill C1 6633.88 tok/s 8876.31 tok/s +33.8%
Prefill C8 6960.00 tok/s 9615.82 tok/s +38.2%
NInfer VRAM 41358 MiB 35106 MiB -15.1%

Performance is hardware- and workload-dependent.

Refusal evaluation

Fixed Swift ORCA-K1 100-prompt evaluation:

Classification Count
DIRECT 90
SAFETY_DEFLECT 10
REFUSE 0
OTHER_FAILURE 0

Configuration: temperature=0, seed=42, max_tokens=1536, thinking disabled.

Historical FP8 responses re-judged with the same current judge produced 87 DIRECT, 12 SAFETY_DEFLECT, 1 REFUSE, and 0 OTHER_FAILURE.

The 0/100 refusals result applies only to this fixed automated evaluation. It is not a universal non-refusal guarantee.

Safety and responsible use

This model has deliberately reduced refusal behavior.

Reduced refusal behavior also reduces model-level safety filtering.
Users are responsible for evaluating the model for their own deployment,
safety, legal, and compliance requirements.

The 0/100 figure describes the documented fixed evaluation set and
inference configuration. It should not be interpreted as a guarantee that
no conceivable prompt, sampling configuration, system prompt, or inference
engine can ever produce a refusal.

Artifact

  • File: Swift-Qwen3.8-27B-Uncensored-NVFP4-LH-ActHeadroom.ninfer
  • Size: 23,719,715,844 bytes
  • SHA-256: a298e28529a31f5447574ba2ad5ba5812d952053292ca017115f9d735dfdadcd
  • Stored objects: 1,246

The artifact contains Text, Vision, MTP, DFlash2, the optimized proposal head, and tokenizer/frontend resources.

Runtime requirements

Validated NInfer revision: f76e19c0fbd026c86f46005acf2c80c54084bade.

Current NInfer targets NVIDIA Blackwell sm_120a. This build was validated on an NVIDIA RTX PRO 6000 Blackwell Workstation Edition.

The current .ninfer runtime should not be considered portable to Ampere, Ada, or Hopper. This limitation primarily comes from the current NInfer execution target, not from the conceptual NVFP4 quantization format itself.

Recommended NInfer server

ninfer-serve \
  ./Swift-Qwen3.8-27B-Uncensored-NVFP4-LH-ActHeadroom.ninfer \
  --host 0.0.0.0 \
  --port 8080 \
  --model-id Swift-Qwen3.8-27B-Uncensored-NVFP4 \
  --max-context 262144 \
  --kv-capacity 262144 \
  --max-concurrency 8 \
  --kv-dtype fp8 \
  --prefill-chunk 1024 \
  --spec dflash2 \
  --draft-tokens 5 \
  --lm-head-draft \
  --preserve-thinking \
  --default-thinking-budget 2048 \
  --vision

--max-context 262144 is the logical ceiling for one request.

--kv-capacity 262144 is a shared Main Text KV pool across concurrently admitted requests. It does not allocate 262144 KV tokens independently to each concurrent request.

Toolchain

  • NInfer: f76e19c0fbd026c86f46005acf2c80c54084bade
  • ModelOpt: 9e3d555aa16038f7b46a631ca603351146c09123
  • llmcompressor: 6693441a7db6984415d524f51ed16a1605bf2fec
  • compressed-tensors: 0.18.1.a20260914

Model lineage

Qwen/Qwen3.8-27B
        ↓
ukisai/Swift-Qwen3.8-27b
        ↓
d0xin/Swift-Qwen3.8-27B-Uncensored-BF16
        ↓
Local-Hessian + Activation Headroom
mixed NVFP4/FP8
        ↓
this NInfer artifact

Limitations

Quantization can change individual generation trajectories even when aggregate benchmark accuracy is similar.

The MMLU-Pro result reported here uses a fixed 280-question subset, not the full benchmark. The refusal evaluation uses a fixed automated 100-prompt set. Performance results were measured on one RTX PRO 6000 Blackwell system and should not be interpreted as universal performance values.

License

This model is a derivative of ukisai/Swift-Qwen3.8-27b.

Swift-specific contributions are distributed under the Swift Open License v1.0. The underlying Qwen base model is distributed under Apache License 2.0.

See the included LICENSE, LICENSE-APACHE-2.0, and NOTICE files for applicable terms and attribution requirements.

Attribution

  • Base model: Qwen/Qwen3.8-27B
  • Swift fine-tune: ukisai/Swift-Qwen3.8-27b
  • Uncensored derivative, quantization, NInfer conversion, and validation: d0xin
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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.