AN

Anime Llasa 3B

AnimeGGUF by mradermacherUpdated 2025-12-07
Download on Hugging Face
Parameters3.41B
Context128K
Layers28
Architecturellama
Smallest quant0.0 GB
Quick answer

Anime Llasa 3B needs about 3.6 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Anime Llasa 3B – 3.41B parameter TTS model for Japanese

Anime Llasa 3B is a 3.41B parameter text‑to‑speech model fine‑tuned for Japanese. It is based on HKUSTAudio/Llasa‑3B and trained on approximately 33,000 hours of data. The model is available in multiple GGUF quantizations.

Good at

  • Japanese TTS
  • Expressive voice synthesis
  • Stable output

Limits

  • No vision support
  • CC‑BY‑NC‑4.0 license
  • Requires 8k context for estimates

Best for

  • Voice‑over production
  • Audiobook narration
  • Language learning tools

Who it’s for. Developers and content creators needing high‑quality Japanese TTS. The model is suitable for projects that can comply with the CC‑BY‑NC‑4.0 license and have sufficient GPU memory for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ1_S1.0 GB 2.4 GB
Fits Get file →
IQ1_M1.1 GB 2.5 GB
Fits Get file →
IQ2_XXS1.2 GB 2.6 GB
Fits Get file →
IQ2_XS1.2 GB 2.7 GB
Fits Get file →
IQ2_S1.3 GB 2.7 GB
Fits Get file →
IQ2_M1.4 GB 2.8 GB
Fits Get file →
Q2_K_S1.4 GB 2.9 GB
Fits Get file →
IQ3_XXS1.5 GB 2.9 GB
Fits Get file →
Q2_K1.5 GB 3.0 GB
Fits Get file →
IQ3_XS1.6 GB 3.1 GB
Fits Get file →
IQ3_S1.7 GB 3.1 GB
Fits Get file →
Q3_K_S1.7 GB 3.1 GB
Fits Get file →
IQ3_M1.8 GB 3.2 GB
Fits Get file →
Q3_K_M1.9 GB 3.3 GB
Fits Get file →
Q3_K_L2.0 GB 3.4 GB
Fits Get file →
IQ4_XS2.0 GB 3.4 GB
Fits Get file →
IQ4_NL2.1 GB 3.5 GB
Fits Get file →
Q4_02.1 GB 3.5 GB
Fits Get file →
Q4_K_S2.1 GB 3.5 GB
Fits Get file →
Q4_K_M2.2 GB 3.6 GB
Fits Get file →
Q4_12.3 GB 3.7 GB
Fits Get file →
Q5_K_S2.4 GB 3.9 GB
Fits Get file →
Q5_K_M2.5 GB 3.9 GB
Fits Get file →
Q6_K2.8 GB 4.3 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.01 GB, 2.4 GB memory) or IQ1_M (1.06 GB, 2.5 GB). For 16 GB VRAM, IQ2_M (1.37 GB, 2.8 GB) or Q3_K_M (1.85 GB, 3.3 GB) are good choices. Higher‑quality Q4_K_M (2.19 GB, 3.6 GB) requires 24 GB VRAM or more.

What GPU do you need for Anime Llasa 3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q5_K_M (2.5 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (2.8 GB file, about 4.3 GB in use).

Which Anime Llasa 3B quant should you choose?

Q4_K_M is the usual starting point for Anime Llasa 3B: it balances file size and quality well. Here it is a 2.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.41B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyAnime
Downloads (HF)980
Last updated2025-12-07

Frequently asked questions about Anime Llasa 3B

How much VRAM does Anime Llasa 3B need?

About 3.6 GB at Q4_K_M with an 8K context window. That is the 2.2 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 Anime Llasa 3B on an 8 GB GPU?

Yes, with Q6_K: the 2.8 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Anime Llasa 3B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.2 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.3 GB and 19 more.

What context length does Anime Llasa 3B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Anime Llasa 3B GGUF?

The files are on Hugging Face in the mradermacher/Anime-Llasa-3B-i1-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 Anime Llasa 3B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Anime Llasa 3B on 8 GB VRAM?

Yes, with IQ1_S or IQ1_M quantizations the estimated VRAM usage is about 2.4–2.5 GB at 8k context.

Does the model support vision inputs?

No, the model only processes text and does not support vision.

What license applies to this model?

The model is licensed under CC‑BY‑NC‑4.0, allowing non‑commercial use with attribution.

Other GGUFs of Anime-Llasa-3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Anime models

All Anime →

Other tiny models

All tiny models →