Qwenio21-Int8wo-quantized is an open-weight model from Herbert Caller. Its published files total 17.1 GB.
Parameters—
Context—
Weights17.1 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- herb786/Qwenio21-Int8wo-quantized
- Publisher
- Herbert Caller
- Task
- Not stated by the source
- Modality
- Other
- Library
- diffusers
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 14191ad8d5ab59845c61a00159782695340b25b3
- First published
- 2026-09-28
- Last updated
- 2026-09-28
Files and Weights
6 files, 17.1 GB in total. The weights are 2 files totalling 17.1 GB in bin, safetensors.
Weights2 files · 17.1 GB
Configuration3 files · 3.2 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| text_encoder/model.safetensors | Weights | 10.0 GB | 6103b0ea0b36 |
| transformer/diffusion_pytorch_model.bin | Weights | 7.1 GB | b394bf260bbc |
| text_encoder/config.json | Configuration | 2.1 KB | — |
| text_encoder/generation_config.json | Configuration | 213 B | — |
| transformer/config.json | Configuration | 884 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 17.1 GB
Download from Herbert Caller
Released by Herbert Caller through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 17.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.