Downloads · 30 days
12
21% of all-time downloads
ubs_autotest-4bit
Catter58/ubs_autotest-4bit
ubs_autotest-4bit is a machine learning model from Catter58. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as apache-2.0.
4-bit GGUF quantization of Catter58/ubsautotest, a fine-tune of Qwen3.6-35B-A3B (MoE).
All-time downloads
56
Public
Repo size
21.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf21.7 GB · 100%
At a glance
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- c6781510
Base models
Model card
From the Hugging Face model README
ubs_autotest-4bit (GGUF Q4_K_M)
4-bit GGUF quantization of Catter58/ubs_autotest, a fine-tune of Qwen3.6-35B-A3B (MoE).
Files
| File | Quant | Size |
|---|---|---|
ubs_autotest-Q4_K_M.gguf | Q4_K_M | see repo |
How it was made
python llama.cpp/convert_hf_to_gguf.py ./ubs_autotest --outfile ubs_autotest-bf16.gguf --outtype bf16
llama-quantize ubs_autotest-bf16.gguf ubs_autotest-Q4_K_M.gguf Q4_K_M
Architecture qwen35moe requires a recent llama.cpp build.
Usage
llama.cpp:
llama-cli -m ubs_autotest-Q4_K_M.gguf -p "Hello"
Ollama:
ollama run hf.co/Catter58/ubs_autotest-4bit:Q4_K_M
Note
The source model is multimodal (image-text-to-text). This GGUF contains the text weights only; the vision encoder is not included.
- Library
- gguf
- License
- apache-2.0
- Languages
- en
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026