Luni/Qwen3.8-27B-Cold-Fusion-GAIN-Heretic-EXL3-4.0bpw

Source: 🤗text-generationapache-2.08.1B params16 GBsafetensors✓ 5 checksumsupdated 16d ago

or submit a torrent

Qwen3.8-27B-Cold-Fusion-GAIN-Heretic-EXL3-4.0bpw

ExLlamaV3 4.0 bpw quantization of Luni/Qwen3.8-27B-Cold-Fusion-GAIN-Heretic.

Specifications

Quantized weight: ~15.4 GB across 4 SafeTensors shards.
Hardware target: 100% VRAM resident on RTX 5090 (32GB) and RTX 4090 (24GB).
Calibration: Fast 4096-token sequence calibration (-ss 4096).
Purpose: Uncensored agentic coding, systems engineering, bash execution, and high-IQ reasoning.

CommentsShare your thoughts and shape the future of sovereign AI.

@Luni is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @Luni

Files and sources

✓SourceAvailable on Hugging Face

2Checksums5 awaiting witness

3TorrentNot listed

4SwarmNot checked

Source revision: 955492c12bab…
Witnessed: Not yet
Weight files: 5
Model size: 16 GB
Downloads · last month: 38
Publisher: Unclaimed

Public checksum record coming on the next sync

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

>_Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Luni/Qwen3.8-27B-Cold-Fusion-GAIN-Heretic-EXL3-4.0bpw ./model-folder