TI

tinyrefinery

TinyrefineryGGUF by adeelahmadUpdated 2024-03-25
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.5 GB
Quick answer

tinyrefinery needs about 5.1 GB of memory at Q3_0 (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

tinyrefinery is a 7.24B-parameter Tinyrefinery model in GGUF format, quantized by adeelahmad. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.5 GB (Q3_0) to 3.5 GB (Q3_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_03.5 GB 5.1 GB
Fits Get file →

What GPU do you need for tinyrefinery?

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 Q3_0 (3.5 GB file, about 5.1 GB in use).

Which tinyrefinery quant should you choose?

Q3_0 (3.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,769 tokens
KV cache (fp16)128 KB per token

Source

Quantized byadeelahmad
Licenseunknown
Downloads (HF)11
Last updated2024-03-25

Frequently asked questions about tinyrefinery

How much VRAM does tinyrefinery need?

About 5.1 GB at Q3_0 with an 8K context window. That is the 3.5 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 tinyrefinery on an 8 GB GPU?

Yes, with Q3_0: the 3.5 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tinyrefinery GGUF?

It depends on the quant: Q3_0 is 3.5 GB.

What context length does tinyrefinery support?

The GGUF header lists a trained context length of 32,769 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download tinyrefinery GGUF?

The files are on Hugging Face in the adeelahmad/tinyrefinery repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does tinyrefinery use?

Hugging Face lists the license as unknown. 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 from adeelahmad

All by adeelahmad →

Other small models

All small models →