AN

AniSora v3

AnisoraGGUF by woctordhoUpdated 2025-09-02
Download on Hugging Face
Parameters16.4B
Context—
Layers—
Architecturewan
Smallest quant10.9 GB
Quick answer

AniSora v3 needs about 12.7 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.9 GB (Q4_K_M) to 32.8 GB (BF16).

AniSora v3 – 16.4B parameter LLM in GGUF format

AniSora v3 is a 16.4 billion parameter language model. It is available in several GGUF quantizations and can be run with llama.cpp. The model offers a balance between size and performance.

Good at

  • Text generation
  • Prompt completion
  • General language tasks

Limits

  • No vision support
  • No license information
  • Context length not specified

Best for

  • Chatbot development
  • Content drafting
  • Code assistance

Who it’s for. Developers and researchers looking for a large language model that can be deployed locally with llama.cpp. The model is suitable for projects that require a 16.4B parameter model without specialized hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M10.9 GB 12.7 GB
Too big Get file →
Q6_K13.8 GB 15.9 GB
Too big Get file →
BF1632.8 GB 37.2 GB
Too big Get file →

For 8‑GB VRAM, the Q4_K_M quantization (10.86 GB file, 12.7 GB memory at 8k context) is too large. The Q6_K quantization (13.75 GB file, 15.9 GB memory) is also too large. The BF16 quantization (32.8 GB file, 37.2 GB memory) is the largest. None of the available quantizations fit within 8 GB VRAM; a smaller model or higher VRAM is required.

What GPU do you need for AniSora v3?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q6_K (13.8 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (13.8 GB file, about 15.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (13.8 GB file, about 15.9 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (32.8 GB file, about 37.2 GB in use).

Which AniSora v3 quant should you choose?

Q4_K_M is the usual starting point for AniSora v3: it balances file size and quality well. Here it is a 10.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters16.4B

Source

Quantized bywoctordho
FamilyAnisora
Downloads (HF)1,486
Last updated2025-09-02

Frequently asked questions about AniSora v3

How much VRAM does AniSora v3 need?

About 12.7 GB at Q4_K_M with an 8K context window. That is the 10.9 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 AniSora v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AniSora v3 GGUF?

It depends on the quant: Q4_K_M is 10.9 GB, Q6_K is 13.8 GB, BF16 is 32.8 GB.

Where can I download AniSora v3 GGUF?

The files are on Hugging Face in the woctordho/AniSora-v3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run AniSora v3 on 8 GB VRAM?

No. The smallest quantization requires 12.7 GB of VRAM at 8k context.

What is the file size of the Q4_K_M quantization?

10.86 GB.

How much memory does the BF16 quantization need at 8k context?

37.2 GB.

Similar models

Browse all →

Other medium models

All medium models →