TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2

Source: 🤗image-text-to-textapache-2.027.8B params56 GBsafetensors✓ 16 checksumsupdated 202d ago

CommentsShare your thoughts and shape the future of sovereign AI.

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

Files and sources

SourceAvailable on 🤗

Checksums16 awaiting witness

TorrentNot listed

SwarmNot checked

Source revision: 41fec5f2e505…
Witnessed: Not yet
Weight files: 16
Model size: 56 GB
Downloads · last month: 97
Publisher: Unclaimed

Public checksum record coming on the next sync

Weights

Original

BF1656 GB
15 files
model-00013-of-00015.safetensors 4.0 GBmodel-00007-of-00015.safetensors 4.0 GBmodel-00001-of-00015.safetensors 4.0 GBmodel-00014-of-00015.safetensors 3.9 GBmodel-00002-of-00015.safetensors 3.9 GBmodel-00009-of-00015.safetensors 3.9 GBmodel-00011-of-00015.safetensors 3.9 GBmodel-00012-of-00015.safetensors 3.9 GBmodel-00003-of-00015.safetensors 3.9 GBmodel-00004-of-00015.safetensors 3.9 GBmodel-00010-of-00015.safetensors 3.9 GBmodel-00005-of-00015.safetensors 3.9 GBmodel-00006-of-00015.safetensors 3.9 GBmodel-00008-of-00015.safetensors 3.9 GBmodel-00015-of-00015.safetensors 509 MB

Family

Quants 2

Finetunes 1

nightmedia/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-mxfp4-mlxadapter

Modified 5

Qwen3.6 27B x Claude Opus 4.x - v2

Benchmarks

Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.665,0.831,0.910,0.790,0.456,0.813,0.772

Qwen3.6-27B
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.647,0.803,0.910,0.773,0.450,0.806,0.742

Provided by @nightmedia. All benchmarks were done in mxfp8 precision

🧬 Datasets:

⚡ Use cases

Coding
Creative Writing
Visual Understanding
General Purpose

Citations and Contributions

@unsloth - This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
@Qwen - Providing a fantastic, native-multimodal base model

Usage

If you need help setting up and configuring this model please follow the Qwen team's instructions in the original model's README

Weights

Original

BF1656 GB
15 files
model-00013-of-00015.safetensors 4.0 GBmodel-00007-of-00015.safetensors 4.0 GBmodel-00001-of-00015.safetensors 4.0 GBmodel-00014-of-00015.safetensors 3.9 GBmodel-00002-of-00015.safetensors 3.9 GBmodel-00009-of-00015.safetensors 3.9 GBmodel-00011-of-00015.safetensors 3.9 GBmodel-00012-of-00015.safetensors 3.9 GBmodel-00003-of-00015.safetensors 3.9 GBmodel-00004-of-00015.safetensors 3.9 GBmodel-00010-of-00015.safetensors 3.9 GBmodel-00005-of-00015.safetensors 3.9 GBmodel-00006-of-00015.safetensors 3.9 GBmodel-00008-of-00015.safetensors 3.9 GBmodel-00015-of-00015.safetensors 509 MB

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 TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2 ./model-folder