Downloads · 30 days
12
24% of all-time downloads
Qwen3-0.6B-ZL-GGUF
negativeonehero/Qwen3-0.6B-ZL-GGUF
Qwen3-0.6B-ZL-GGUF is a machine learning model from negativeonehero. 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.
ZL-GGUF is a series of quantized models where I push quantization to the limits.
All-time downloads
50
Public
Repo size
425 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf425 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 26, 2025
- Updated
- Jun 26, 2025
- SHA
- 521f011e
Base models
Model card
From the Hugging Face model README
ZL-GGUF
ZL-GGUF is a series of quantized models where I push quantization to the limits.
Using layer statistics tools, one can implement a set of quantization rules to minimize quality loss while providing better quantization efficiency (hence the name Zero Loss - ZL).
How to run
To run these models, you can use llama.cpp or any llama.cpp wrappers like ollama, LM Studio... For models with IQx_K quantization which is my main scope, use ik_llama.cpp instead. Note that Hugging Face may not show the correct quantization for the file, please go to the Files tab or view its properties.
- License
- apache-2.0
- Created
- Jun 26, 2025
- Updated
- Jun 26, 2025