Downloads · 30 days
50
16% of all-time downloads
Sentia-Qwen3.5-9B-GGUF
BucketP/Sentia-Qwen3.5-9B-GGUF
Sentia-Qwen3.5-9B-GGUF is a text generation model from BucketP. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This repository contains the GGUF format models for the Sentia AI VTuber Project. Base Model: lukey03/Qwen3.5-9B-abliterated
All-time downloads
305
Public
Repo size
23.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf23.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026
- SHA
- 7e7f6ba8
Base models
Model card
From the Hugging Face model README
Sentia-Qwen3.5-9B-GGUF
This repository contains the GGUF format models for the Sentia AI VTuber Project.
Base Model: lukey03/Qwen3.5-9B-abliterated
Provided Files & VRAM Requirements
We provide both the full-precision (FP16) version for high-end GPUs and the quantized (Q4_K_M) version for edge deployment.
| Filename | Quant Method | File Size | Recommended VRAM | Use Case |
|---|---|---|---|---|
Sentia-9B-FP16.gguf | FP16 (Unquantized) | ~18.0 GB | 24GB+ | Highest precision. Recommended for server-side inference (e.g., RTX 3090/4090). |
Sentia-Q4_K_M.gguf | Q4_K_M | ~5.3 GB | 8GB - 16GB | Excellent balance of speed and quality. Recommended for local Edge deployment (e.g., RX 9070 XT). |
Usage with llama.cpp
For Edge Inference (Q4):
./llama-server -m Sentia-Q4_K_M.gguf -ngl 99 --port 8080 --chat-template chatml
For High-Precision Inference (FP16)
./llama-server -m Sentia-9B-FP16.gguf -ngl 99 --port 8080 --chat-template chatml
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Languages
- zh
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026