license: apache-2.0
base_model: bottlecapai/ThinkingCap-Qwen3.6-27B
base_model_relation: quantized
pipeline_tag: text-generation
library_name: vllm
tags:
- nvfp4
- compressed-tensors
- mtp
- abliterated
- uncensored
- security
- qwen3.6
extra_gated_prompt: >-
This model is DEPRECATED and no longer distributed. Access requests are not
being reviewed or approved.
ThinkingCap-Qwen3.6-27B-abliterated NVFP4 (vLLM)
[!WARNING]
DEPRECATED — 2026-08-07. This release has been withdrawn and is no longer
distributed or maintained. Access is gated and requests will not be approved.
No successor is designated.
Refusal-free ThinkingCap for authorized malware and vulnerability analysis, pentesting, and
defensive security research. NVFP4 (compressed-tensors) for vLLM on Blackwell (sm120), 256K
context, with the base model's capability preserved. Companion to the
GGUF release.
protoLabsAI · Qwen3.6-27B lineage · vLLM (compressed-tensors NVFP4)
⚠️ Dual-use, read first
This is an abliterated (refusal-free) model. It produces working exploit PoCs, offensive
tooling, and attack reasoning without guardrails, by design, because built-in refusals sabotage
authorized security work. The safety boundary lives with the operator, not the weights. Intended
strictly for authorized pentest, red-team, blue-team, malware and vulnerability analysis, CTF, and
find→prove→fix research on systems you own or are permitted to test. Not for unauthorized access,
targeting third parties, or abuse.
Why refusal-free
Digital attacks keep getting more sophisticated and more automated, and defenders, analysts, and
security researchers need tools that can keep pace. Built-in refusals handicap only the authorized
side: an attacker does not reach for a guarded model, while a defender trying to reverse a malware
sample or prove a vulnerability before it is exploited gets stopped cold by one. A refusal-free
model puts that capability, and the governance of how it is used, back in the operator's hands.
The tradeoff to watch with any abliteration is capability loss. We measured it: refusal-free (0/4 on
real malware/vuln/exploit/pentest tasks; 3.6% on a 192-prompt offensive probe), and coding preserved
(LiveCodeBench hard, exec-graded: matches the clean ThinkingCap base). Abliteration did not cost
ThinkingCap its capability.
Serve
vllm serve protoLabsAI/ThinkingCap-Qwen3.6-27B-abliterated-NVFP4 \
--served-model-name abliterated --reasoning-parser qwen3 \
--enable-auto-tool-choice --tool-call-parser qwen3_xml \
--max-model-len 262144 --kv-cache-dtype fp8 --linear-backend marlin
--linear-backend marlinis required on sm120 (Blackwell). The auto-selected FP4 GEMM
JIT-fails ("No supported CUDA architectures for [12]"); Marlin is the working NVFP4 path.- Recommended sampling:
temperature 0.6, top_p 0.95, top_k 20. Do not use greedy decoding.
MTP
An mtp.* draft head ships in the artifact (model_mtp.safetensors). Speculative decoding is
delivered via the GGUF release
(--spec-type draft-mtp, +44% decode); the vLLM build currently serves NVFP4 without spec-decode.
Provenance and recipe
- Base: bottlecapai/ThinkingCap-Qwen3.6-27B (Qwen3.6-27B reasoning finetune, native MTP).
- Abliteration: Heretic (single-direction refusal ablation, bf16).
- NVFP4: llm-compressor (compressed-tensors), ignore list covers
lm_head, vision tower, DeltaNet linear-attn, and the MTP head (kept bf16). The MTP head is grafted from the base ThinkingCap.
Need a different format?
Open a Community discussion. GGUF quants (bf16 to IQ2, all with MTP baked in) are in the
companion repo.
Safety note (abliterated model): refusal rate is reported above, not gated. This is a security
tool; scope and authorization are the operator's responsibility.