QW

Sakura 1B8 Qwen2beta v0.9

QwenGGUF by ShenSheiBotUpdated 2024-02-27
Download on Hugging Face
Parameters1.84B
Context32K
Layers24
Architectureqwen2
Smallest quant3.7 GB
Quick answer

Sakura 1B8 Qwen2beta v0.9 needs about 5.8 GB of memory at F16 (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.7 GB (F16) to 28.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Sakura 1B8 Qwen2beta v0.9 is a 1.84B-parameter Qwen model in GGUF format, quantized by ShenSheiBot. Its trained context length is 32K tokens. The repository has 2 quant files, from 3.7 GB (F16) to 28.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F163.7 GB 5.8 GB
Fits Get file →
F1628.3 GB 30.5 GB
Too big Get file →

What GPU do you need for Sakura 1B8 Qwen2beta v0.9?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (28.3 GB file, about 30.5 GB in use).

Which Sakura 1B8 Qwen2beta v0.9 quant should you choose?

F16 (3.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.84B
Layers24
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byShenSheiBot
FamilyQwen
Licensegpl-3.0
Downloads (HF)99
Last updated2024-02-27

Frequently asked questions about Sakura 1B8 Qwen2beta v0.9

How much VRAM does Sakura 1B8 Qwen2beta v0.9 need?

About 5.8 GB at F16 with an 8K context window. That is the 3.7 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 1B8 Qwen2beta v0.9 on an 8 GB GPU?

Yes, with F16: the 3.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sakura 1B8 Qwen2beta v0.9 GGUF?

It depends on the quant: F16 is 3.7 GB, F16 is 28.3 GB.

What context length does Sakura 1B8 Qwen2beta v0.9 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Sakura 1B8 Qwen2beta v0.9 GGUF?

The files are on Hugging Face in the ShenSheiBot/Sakura-1B8-Qwen2beta-v0.9-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 1B8 Qwen2beta v0.9 use?

Hugging Face lists the license as gpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →