Anima aesthetic v1.0 needs about 2.1 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.0 GB (Q3_K_M) to 2.2 GB (Q8_0).
Anima aesthetic v1.0 – 2 B parameter text‑to‑image model for anime‑style art
Anima aesthetic v1.0 is a 2.09 B parameter text‑to‑image model built on the Cosmos architecture. It is fine‑tuned for consistent, high‑quality anime and non‑photorealistic illustrations. The model is optimized for illustration generation rather than realism.
Good at
- Anime character illustration
- Consistent art style
- High‑quality default aesthetics
Limits
- No realism support
- Requires 8 k context for full memory estimates
- License is other
Best for
- Illustration creation
- Anime concept art
- Creative illustration workflows
Who it’s for. Artists and designers looking for fast, consistent anime‑style image generation. The model works best in ComfyUI with the GGUF format and a compatible VAE and text encoder.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_M | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q5_K_M | 1.6 GB | 2.2 GB | Fits | Get file → | |
| Q6_K | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 2.2 GB | 3.0 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (1.27 GB file, ~1.9 GB memory at 8k context) is recommended. If more VRAM is available, Q5_K_M (1.56 GB file, ~2.2 GB memory) offers better fidelity. Larger quants like Q6_K or Q8_0 require more than 2 GB memory and are suited for high‑end GPUs.
What GPU do you need for Anima aesthetic v1.0?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 3.0 GB in use).
Which Anima aesthetic v1.0 quant should you choose?
Q4_K_M is the usual starting point for Anima aesthetic v1.0: it balances file size and quality well. Here it is a 1.4 GB file.
The Q8_0 file is 2.2 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_M at 1.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Anima aesthetic v1.0
How much VRAM does Anima aesthetic v1.0 need?
About 2.1 GB at Q4_K_M with an 8K context window. That is the 1.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Anima aesthetic v1.0 on an 8 GB GPU?
Yes, with Q8_0: the 2.2 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Anima aesthetic v1.0 GGUF?
It depends on the quant: Q3_K_M is 1.0 GB, Q4_K_S is 1.3 GB, Q4_K_M is 1.4 GB, Q5_K_M is 1.6 GB, Q6_K is 1.7 GB, Q8_0 is 2.2 GB.
Where can I download Anima aesthetic v1.0 GGUF?
The files are on Hugging Face in the Abiray/Anima-aesthetic-v1.0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Anima aesthetic v1.0 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Anima aesthetic v1.0 on 8 GB VRAM?
Yes, Q4_K_M uses about 1.9 GB memory at 8k context, fitting within 8 GB VRAM limits.
What resolution does the model support?
It generates images between 512² and 1536² pixels.
Do I need a special VAE?
Yes, the model requires qwen_image_vae.safetensors for proper image decoding.