license: apache-2.0 base_model: Qwen/Qwen3.6-27B pipeline_tag: image-text-to-text library_name: transformers tags:

uncensored
abliterated
nvfp4
compressed-tensors
qwen3_5
mtp
v100

Qwen3.6 27B Uncensored Medium NVFP4

Medium tier in NVFP4 for Tesla V100.

Part of the Qwen3.6-27B Uncensored — base collection — abliterated (Heretic) Qwen3.6 vision-language models served on Tesla V100 via 1Cat-vLLM.

What this is

Medium — gentle abliteration on the standard base: a middle openness point (0.25) — more open than the ThinkingCap tiers, lighter reasoning than Aggressive.

NVFP4 — 4-bit NVFP4A16 (compressed-tensors: E2M1 weights + FP8-E4M3 group scales + FP32 global). Built for the 1Cat-vLLM SM70 TurboMind kernel on Tesla V100; ships an MTP head for speculative decoding.

Base model: Qwen/Qwen3.6-27B

Serving

# 1Cat-vLLM on 2x Tesla V100 (SM70): NVFP4 weight-only + MTP speculative decoding.
export VLLM_SM70_FLASH_ATTN_V100=1 VLLM_SM70_QUANT_BACKEND=turbomind VLLM_SM70_NVFP4_TURBOMIND=1
python -m vllm.entrypoints.openai.api_server \
  --model philbert440/Qwen3.6-27B-Uncensored-Medium-NVFP4 --trust-remote-code --dtype half \
  --attention-backend FLASH_ATTN_V100 --tensor-parallel-size 2 \
  --kv-cache-dtype fp8_e5m2 --max-num-seqs 6 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":4,"attention_backend":"FLASH_ATTN_V100","draft_sample_method":"greedy"}' \
  --compilation-config '{"cudagraph_mode":"full_and_piecewise","cudagraph_capture_sizes":[1,2,4,8]}'

V100 note: the full_and_piecewise cudagraph mode + greedy MTP are required — a plain full cudagraph capture corrupts the SM70 NVFP4 path into garbage (fixed as a default in 1Cat-vLLM #174; on older builds also set VLLM_SM70_MTP_DYNAMIC_DRAFT_VOCAB_DEFAULT=0).

Openness

Openness profile (honest): abliteration opens up hacking / malware / lock-picking / NSFW / disinformation prompts; weapons, drugs, political persuasion, surveillance, and extremism stay refused across all tiers. "Uncensored" here means cyber/NSFW-permissive, not unconditionally open.

Variants

See the Qwen3.6-27B Uncensored — base collection for all tiers and formats (BF16 / W4A16-AWQ / NVFP4).

Abliteration removes safety refusals; you are responsible for lawful, ethical use.

Changelog

2026-08-15 — tokenizer fix. tokenizer.json / tokenizer_config.json were re-serialized by the llm-compressor calibration run and shipped with an active truncation block (max_length 1024/2048) plus a drifted pre-tokenizer regex (and, on the Qwen3.6-based repos, 7 phantom audio/TTS special tokens the base model does not define). That broke image inputs larger than the limit under transformers 5 / vLLM (Mismatch in image token count, surfacing as an HTTP 400 Failed to apply Qwen3VLProcessor). Both files are now byte-identical to the upstream base model's (vocab/merges/added tokens were always identical — this is a metadata-only restore). If you downloaded before this date, re-fetch those two files. Thanks to @elBuffo for the report.

What this is

Medium — gentle abliteration on the standard base: a middle openness point (0.25) — more open than the ThinkingCap tiers, lighter reasoning than Aggressive.

Serving

# 1Cat-vLLM on 2x Tesla V100 (SM70): NVFP4 weight-only + MTP speculative decoding. export VLLM_SM70_FLASH_ATTN_V100=1 VLLM_SM70_QUANT_BACKEND=turbomind VLLM_SM70_NVFP4_TURBOMIND=1 python -m vllm.entrypoints.openai.api_server \ --model philbert440/Qwen3.6-27B-Uncensored-Medium-NVFP4 --trust-remote-code --dtype half \ --attention-backend FLASH_ATTN_V100 --tensor-parallel-size 2 \ --kv-cache-dtype fp8_e5m2 --max-num-seqs 6 \ --speculative-config '{"method":"mtp","num_speculative_tokens":4,"attention_backend":"FLASH_ATTN_V100","draft_sample_method":"greedy"}' \ --compilation-config '{"cudagraph_mode":"full_and_piecewise","cudagraph_capture_sizes":[1,2,4,8]}'

V100 note: the full_and_piecewise cudagraph mode + greedy MTP are required — a plain full cudagraph capture corrupts the SM70 NVFP4 path into garbage (fixed as a default in 1Cat-vLLM #174; on older builds also set VLLM_SM70_MTP_DYNAMIC_DRAFT_VOCAB_DEFAULT=0).

Changelog

2026-08-15 — tokenizer fix. tokenizer.json / tokenizer_config.json were re-serialized by the llm-compressor calibration run and shipped with an active truncation block (max_length 1024/2048) plus a drifted pre-tokenizer regex (and, on the Qwen3.6-based repos, 7 phantom audio/TTS special tokens the base model does not define). That broke image inputs larger than the limit under transformers 5 / vLLM (Mismatch in image token count, surfacing as an HTTP 400 Failed to apply Qwen3VLProcessor). Both files are now byte-identical to the upstream base model's (vocab/merges/added tokens were always identical — this is a metadata-only restore). If you downloaded before this date, re-fetch those two files. Thanks to @elBuffo for the report.