Anima-2.9B (GGUF Quantized Format)
Quantized GGUF weights for Anima-2.9B by Gazingstars123 for efficient inference in ComfyUI using ComfyUI-GGUF.
📌 Disclaimer & Attribution
- Original Model: Developed by Gazingstars123 based on circlestone-labs/Anima.
- Conversion: Converted to GGUF format by vanes430.
- License: CircleStone Labs Non-Commercial License.
Support original author: Ko-fi | PayPal
Available Quantizations
| Filename | Quant Type | Size | Recommended VRAM | Quality |
|---|---|---|---|---|
Anima-2.9B-preview-v1-Q8_0.gguf |
Q8_0 | ~3.15 GB | 6GB+ | ⭐️ Best Quality (Near Lossless) |
Anima-2.9B-preview-v1-Q5_0.gguf |
Q5_0 | ~2.10 GB | 4GB - 6GB | High Quality / Balanced |
Anima-2.9B-preview-v1-Q4_0.gguf |
Q4_0 | ~1.75 GB | 4GB | Fast / Low VRAM |
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
8-bit
Model tree for vanes430/Anima-2.9B-GGUF
Base model
nvidia/Cosmos-Predict2-2B-Text2Image Finetuned
circlestone-labs/Anima Finetuned
Gazingstars123/Anima-2.9B