← back to catalog · registered 2026-09-11 14:55

esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-W4A16-T400

esatapedico 27B second-order
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 2026-09-11

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
Languages
en multilingual
Tags
transformers safetensors qwen3_5_text text-generation nvfp4 qwen3.8 qwen3.5 blackwell mtp speculative-decoding turbo twin-turbo

Related

Total size
18.3 GB
Files
9
Quantizations
1
Registered
2026-09-11 14:55
Last updated on HF
2026-09-11 17:19

Files by quantization

Auxiliary files 9 files 18.3 GB
model.safetensors 18.3 GB 29da57b8 download
tokenizer.json 19.1 MB 87a7830d download
chat_template.jinja 16.5 KB be33c51b download
config.json 8.02 KB de3e4fbe download
README.md 3.09 KB 8eb068b3 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.07 KB e15d4cc3 download
recipe.yaml 308 B d9d90bbd download
generation_config.json 213 B 79c8cce3 download

README current version from Hugging Face


license: apache-2.0
base_model: DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
pipeline_tag: text-generation
library_name: transformers
tags:

  • nvfp4
  • qwen3.8
  • qwen3.5
  • blackwell
  • mtp
  • speculative-decoding
  • turbo
  • twin-turbo
  • fable
  • cold-fusion
  • compressed-tensors
  • vllm
    language:
  • en
  • multilingual
    quantization_config:
    quant_method: compressed-tensors
    format: nvfp4-pack-quantized

Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-W4A16-T400

NVFP4 checkpoint of DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored, quantized for vLLM serving. NVFP4 here means W4A16 with FP8 scales, group size 16, weight only, about 400 tensors. No calibration data was used.

HF repo: esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-W4A16-T400

At a glance

Field Value
Format compressed-tensors nvfp4-pack-quantized
Quantization W4A16, group size 16, FP8 E4M3 scales, weight only, 400 NVFP4 tensors
Kept in BF16 lm_head, vision tower, MTP head, DeltaNet conv1d and in_proj_a/b
Calibration none
Base DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored (Qwen3.8-27B, Apache 2.0)

Quantized set covers the MLP on all 64 layers, Q, K, V, O on the 16 full attention layers, the token embeddings, and the DeltaNet in_proj_qkv/z/out_proj tensors. The lm_head stays at full precision on purpose: vLLM runs the output head unquantized regardless, and no vLLM release loads a compressed-tensors NVFP4 head, so quantizing it only breaks serving with zero runtime gain. Vision tower, MTP head, and the DeltaNet conv1d plus in_proj_a/b dynamics stay at full precision following the JC1DA exception pattern.

Serving

Built for vLLM and engines consuming vLLM-compatible compressed-tensors checkpoints, following the JC1DA-style exception pattern. Verified serving: tensor parallel 2, 2048 context, 9 GB per GPU with ample KV headroom, coherent generation. Serve with --quantization compressed-tensors semantics (auto-detected from the config); FP8 KV remains a runtime flag, not checkpoint bytes. Keep vision intact and MTP for speculative decoding; no GGUF inside this repo.

Checkpoint

  • Single model.safetensors about 19 GB
  • config.json quantization_config.format=nvfp4-pack-quantized, quant_method=compressed-tensors, Qwen3_5ForCausalLM, 64 layers, hybrid GatedDeltaNet, 262144 context, MTP head
  • tokenizer.json intact, chat template intact

Provenance

Derivative of DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored (Apache 2.0) which itself derives from Qwen/Qwen3.8-27B. The TWIN-TURBO tune targets reduced thinking tokens with matched output quality. Exception pattern follows the JC1DA INT4-W4A16 reference. A companion GGUF-parent checkpoint with the conservative 256-tensor recipe lives at esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4.

License

apache-2.0

Card written with AI assistance.

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.