Downloads · 30 days
99
1% of all-time downloads
Qwen3.6-27B-autoround-nvfp4-linearattn-BF16
kaitchup/Qwen3.6-27B-autoround-nvfp4-linearattn-BF16
Qwen3.6-27B-autoround-nvfp4-linearattn-BF16 is a machine learning model from kaitchup. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
<div align="center" <img src="https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/mj6xac74jHGLqymiovObc.png" alt="The Kaitchup -- AI on a Budget" style="width: 100%; max-width: 100%; height:…
All-time downloads
12.1K
Public
Parameters
19.1B
28.6 GB on disk
Likes
11
Public
Repo makeup
Click a slice to open those files.
.safetensors28.6 GB · 100%
Parameter types
How the weights are stored.
U89.4B · 48%
Base models
Model card
From the Hugging Face model README
<div align="center">
<img
src="https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/mj6xac74jHGLqymiovObc.png"
alt="The Kaitchup -- AI on a Budget"
style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
/>
<div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;">
<a href="https://kaitchup.substack.com/subscribe"><strong>Subscribe and Support</strong></a>
</div>
</div>
MTP doesn't seem to work. Use kaitchup/Qwen3.6-27B-autoround-nvfp4-linearattn-mtp-BF16 instead.
This is Qwen/Qwen3.6-27B quantized with AutoRound to NVFP4 with linear-attention layers kept in 16-bit. The model is compatible with vLLM (tested: v0.19). Tested with an RTX Pro 6000. Currently under evaluation. Similar quantization with Qwen3.5 worked very well.
- Developed by: The Kaitchup
Instructions
uv pip install vllm
uv pip install git+https://github.com/huggingface/transformers.git
vllm serve [this model ID] --max-model-len 262144 --reasoning-parser qwen3
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Apr 24, 2026
- Updated
- May 7, 2026