RE

Refact

RefactGGUF by imi1Updated 2023-09-26
Download on Hugging Face
Parameters1.59B
Context4K
Layers32
Architecturerefact
Smallest quant3.2 GB
Quick answer

Refact needs about 3.7 GB of memory at F16 (a 3.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Refact is a 1.59B-parameter Refact model in GGUF format, quantized by imi1. Its trained context length is 4K tokens. The repository has 1 quant file, from 3.2 GB (F16) to 3.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F163.2 GB 3.7 GB
Fits Get file →

What GPU do you need for Refact?

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 F16 (3.2 GB file, about 3.7 GB in use).

Which Refact quant should you choose?

F16 (3.2 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

Architecturerefact
Parameters1.59B
Layers32
Trained context4,096 tokens
KV cache (fp16)8 KB per token

Source

Quantized byimi1
FamilyRefact
Downloads (HF)20
Last updated2023-09-26

Frequently asked questions about Refact

How much VRAM does Refact need?

About 3.7 GB at F16 with an 8K context window. That is the 3.2 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 Refact on an 8 GB GPU?

Yes, with F16: the 3.2 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Refact GGUF?

It depends on the quant: F16 is 3.2 GB.

What context length does Refact support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 4K.

Where can I download Refact GGUF?

The files are on Hugging Face in the imi1/refact-1.6B-fim-f16-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from imi1

All by imi1 →

More Refact models

All Refact →

Other tiny models

All tiny models →