Downloads · 30 days
7
11% of all-time downloads
DBMe/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-exl3-mul1
Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-exl3-mul1 is a text generation model from DBMe. Use it when you need the model to write or continue text. It is set up for exllamav3. The card lists the license as apache-2.0.
EXL3 (ExLlamaV3) quantizations of llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved. All credit for the original model goes to the original authors.
Downloads · 30 days
7
11% of all-time downloads
All-time downloads
66
Public
Repo size
59.7 GB
Likes
0
Public
Click a slice to open those files.
.png77.5 KB · 93%
From the Hugging Face model README
EXL3 (ExLlamaV3) quantizations of llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved. All credit for the original model goes to the original authors.
The model weights are stored in separate branches. Please switch to a branch to download. Note: VRAM estimates include PyTorch context overhead (~0.8GB) and assume an unquantized FP16 KV cache.
| Target BPW | Head BPW | Branch (Download Link) | WikiText-2 PPL (512 ctx)¹ | 2K ctx | 4K ctx | 8K ctx | 16K ctx | 32K ctx |
|---|---|---|---|---|---|---|---|---|
| 4.0 | h6 | 4.0bpw_h6 | 8.0243 | N/A | N/A | N/A | N/A | N/A |
| 5.0 | h6 | 5.0bpw_h6 | 8.0138 | ~16.43 GB | ~16.56 GB | ~16.81 GB | ~17.31 GB | ~18.31 GB |
| 6.0 | h6 | 6.0bpw_h6 | 7.9956 | ~19.26 GB | ~19.39 GB | ~19.64 GB | ~20.14 GB | ~21.14 GB |
¹ Evaluated against WikiText-2 with ExLlamaV3 using a strided 512-token context window (-c 512) in llama.cpp parity mode (-g). Lower is better.
(Higher BPW = higher quality, lower BPW = fits in less VRAM).
It's recommended to use the huggingface-cli to download specific branches. (Do not use git clone as it will download all branches!)
Ensure you have the CLI installed:
pip install -U "huggingface_hub[cli]"
Download a specific branch (e.g., 5.0bpw_h6):
# Example: Downloading the 5.0bpw_h6 branch
huggingface-cli download DBMe/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-exl3-mul1 --revision 5.0bpw_h6 --local-dir Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-exl3-mul1-5.0bpw_h6
These models are highly optimized for modern GPUs and can be run using:
model_name to the local folder name you downloaded the branch into)exllamav3 loader)(Lower is better)

Codebook: mul1
Output Scales: always
Calibration Rows: 250
Calibration Cols: 2048
Calibration Dataset: ExLlamaV3 Default (Wiki/C4/Code)
High Quality (HQ) Mode: False
ExLlamaV3: 1.0.0 (Commit: cb7f2e9)
Hardware: NVIDIA RTX PRO 6000 Blackwell Server Edition