Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUF
2.5B open-weight LLM by webmp3
Live
Open / InstallLast updated October 23, 2026
Description
Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUF is an open-weight text-generation model with roughly 2.5B parameters published by webmp3 on the Hugging Face Hub. It has 1,688 downloads. Runs with gguf.
Community Metrics
Views
4
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
webmp3
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- sakura
- sakura-micro
- llama.cpp
- moe
- qwen4exp
- expert-pruning
- strix-halo
- experimental
Capabilities
- Text generation
- Conversational
- GGUF quantised builds
- Library: gguf
- 2.5B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 10, 2026