sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP

Text Generation·sakamakismile· 44.7K· 62

vllm apache-2.0 Text Generation 17.1B params license:apache-2.0

NVFP4 (modelopt W4A4) quant of Huihui-Qwen3.6-27B-abliterated — a Qwen3.5-family hybrid model (linear attention + periodic full attention) with a built-in MTP (multi-token-prediction) head for speculative decoding. Multimodal-capable (Qwen35ForConditionalGeneration, vision/video tokens) but served here as a text generation / reasoning + tool-calling model. Fits 4× 16 GB Blackwell (SM120).

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP

Model details

Task

Text Generation

Provider

sakamakismile

Framework

vllm

Parameters

17.1B

Size

19 GB

License

apache-2.0

Downloads

44.7K

Likes

Updated

2026-05-31

About sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP

Related Text Generation

Q Qwen/Qwen3-0.6B Text Generation ·751.6M params 27.8M 1.4K 🤗 HF G openai-community/gpt2 Text Generation ·137.0M params 13.3M 3.3K 🤗 HF Q Qwen/Qwen3-8B Text Generation ·8.2B params 13.0M 1.2K 🤗 HF Q Qwen/Qwen2.5-7B-Instruct Text Generation ·7.6B params 12.8M 1.4K 🤗 HF O facebook/opt-125m Text Generation 12.3M 267 🤗 HF Q Qwen/Qwen2.5-1.5B-Instruct Text Generation ·1.5B params 11.3M 748 🤗 HF

Browse all Text Generation models →