SA

Sakura d1 3B HighQuality

GGUFGGUF by webmp3Updated 2026-10-08
Download on Hugging Face
Parameters2.7B
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

Sakura d1 3B HighQuality needs about 2.3 GB of memory at its main file (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 2.3 GB.

Sakura d1 3B HighQuality – a 2.7B parameter decision model in GGUF format

Sakura d1 3B HighQuality is a 2.7B parameter decision model derived from LiquidAI/d1-3B. It supports multimodal input and returns calibrated answers with zero output tokens. The model is available in several GGUF quantizations.

Good at

  • Zero‑output decision answering
  • Multimodal text and image states
  • Fast inference on modern GPUs

Limits

  • No chat or text generation
  • Requires 8k context for memory estimates
  • License is LFM Open License v1.0

Best for

  • Routing and triage systems
  • Moderation pipelines
  • Agent guardrails

Who it’s for. Engineers building decision‑making pipelines that need quick, calibrated yes/no or choice outputs. The model is ideal for systems that require multimodal input but do not need text generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—1.6 GB 2.2 GB
Fits Get file →
—1.7 GB 2.3 GB
Fits Get file →
—1.9 GB 2.7 GB
Fits Get file →
—2.3 GB 3.1 GB
Fits Get file →

For 8 GB VRAM use the 1.56 GB file (est. 2.2 GB RAM at 8k context). For 12 GB VRAM use the 1.95 GB file (est. 2.7 GB RAM). For 16 GB VRAM use the 2.35 GB file (est. 3.1 GB RAM). Estimates are approximate.

What GPU do you need for Sakura d1 3B HighQuality?

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 the main file (2.3 GB file, about 3.1 GB in use).

Which Sakura d1 3B HighQuality quant should you choose?

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

Parameters2.7B

Source

Quantized bywebmp3
Base modelLiquidAI/d1-3B
Licenseother
Downloads (HF)1,674
Last updated2026-10-08

Frequently asked questions about Sakura d1 3B HighQuality

How much VRAM does Sakura d1 3B HighQuality need?

About 2.3 GB at its main file with an 8K context window. That is the 1.7 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 Sakura d1 3B HighQuality on an 8 GB GPU?

Yes, with the smaller files: the 2.3 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sakura d1 3B HighQuality GGUF?

It depends on the quant: file is 0.0 GB, file is 1.6 GB, file is 1.7 GB, file is 1.9 GB, file is 2.3 GB.

Where can I download Sakura d1 3B HighQuality GGUF?

The files are on Hugging Face in the webmp3/Sakura-d1-3B-HighQuality-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 Sakura d1 3B HighQuality 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 Sakura d1 3B HighQuality on 8 GB VRAM?

Yes, the 1.56 GB GGUF file requires about 2.2 GB of RAM at 8k context, which fits on 8 GB VRAM with headroom.

Does this model support text generation?

No, it is a decision model and returns zero output tokens; it does not generate text.

What license applies to the GGUF files?

The files are released under the LFM Open License v1.0, as stated in the repository.

Other GGUFs of d1-3B

Similar models

Browse all →

More from webmp3

All by webmp3 →

Other tiny models

All tiny models →