Downloads · 30 days
0
Qwen3.8-27B-NQ-UD-IQ2-M
agiws/Qwen3.8-27B-NQ-UD-IQ2-M
Qwen3.8-27B-NQ-UD-IQ2-M is a machine learning model from agiws. 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.
⚠️ EXPERIMENTAL REPOSITORY - the model is not functional yet and is under active development.
Access
Public
Updated Aug 24, 2026
Repo size
65.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt65.2 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 22, 2026
- Updated
- Aug 24, 2026
- SHA
- b972e41f
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-NQ-UD-IQ2_M
⚠️ EXPERIMENTAL REPOSITORY - the model is not functional yet and is under active development.
Quantization of Qwen3.8-27B using the UD (Unsloth Dynamic) / IQ2_M scheme with NeuralQuant (NQ) tools.
- NQ - NeuralQuant (our quantizer)
- UD - Unsloth Dynamic: different layers use different bit-widths (sensitive layers are kept more precise)
- IQ2_M - llama.cpp quantization scheme (~2.7-3.0 bpw): a mix of IQ2_S / IQ3_S / Q4_K / Q5_K
Status: the library is preparing the GGUF writer and packers; model files will be published later.
- License
- apache-2.0
- Created
- Aug 22, 2026
- Updated
- Aug 24, 2026