AN

Anything

AnythingGGUF by mzwingUpdated 2024-03-15
Download on Hugging Face
Parameters1.07B
Context—
Layers—
Architecture—
Smallest quant1.3 GB
Quick answer

Anything needs about 2.3 GB of memory at Q5_0 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 30 quants, from 1.3 GB (F16) to 2.1 GB (F16).

1.07B Anything model in GGUF format

Anything is a 1.07B parameter model available in multiple GGUF quantizations. It is hosted on the mzwing/Anything-GGUF repository and can be used with llama.cpp. No additional context or training data details are provided.

Good at

  • Small model size
  • Low memory footprint
  • Versatile usage

Limits

  • No vision support
  • No license information
  • Limited context length details

Best for

  • Local inference
  • Low‑resource deployment
  • Quick prototyping

Who it’s for. Developers and researchers needing a lightweight LLM for local use. The model is suitable for environments with limited GPU memory and where quick loading is important.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.3 GB 1.9 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q5_01.6 GB 2.3 GB
Fits Get file →
Q5_01.6 GB 2.3 GB
Fits Get file →
Q5_01.6 GB 2.3 GB
Fits Get file →
Q5_01.6 GB 2.3 GB
Fits Get file →
Q5_01.6 GB 2.3 GB
Fits Get file →
Q5_11.6 GB 2.3 GB
Fits Get file →
Q5_11.6 GB 2.3 GB
Fits Get file →
Q5_11.6 GB 2.3 GB
Fits Get file →
Q5_11.6 GB 2.3 GB
Fits Get file →
Q5_11.6 GB 2.3 GB
Fits Get file →
Q8_01.8 GB 2.5 GB
Fits Get file →
Q8_01.8 GB 2.5 GB
Fits Get file →
Q8_01.8 GB 2.5 GB
Fits Get file →
Q8_01.8 GB 2.5 GB
Fits Get file →
Q8_01.8 GB 2.5 GB
Fits Get file →
F161.9 GB 2.6 GB
Fits Get file →
F162.1 GB 2.9 GB
Fits Get file →
F162.1 GB 2.9 GB
Fits Get file →
F162.1 GB 2.9 GB
Fits Get file →

For 8 GB VRAM use Q4_0 or Q4_1 (≈2.3 GB memory at 8k context). For 12 GB VRAM use Q5_0 or Q5_1 (≈2.3 GB). For higher precision use F16 (≈2.6–2.9 GB). File sizes range from 1.28 GB to 2.13 GB.

What GPU do you need for Anything?

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 F16 (2.1 GB file, about 2.9 GB in use).

Which Anything quant should you choose?

Q5_0 (1.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is F16 at 1.3 GB, with the quality trade-offs that come with fewer bits. 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

Parameters1.07B

Source

Quantized bymzwing
FamilyAnything
Downloads (HF)1,119
Last updated2024-03-15

Frequently asked questions about Anything

How much VRAM does Anything need?

About 2.3 GB at Q5_0 with an 8K context window. That is the 1.6 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 Anything on an 8 GB GPU?

Yes, with F16: the 2.1 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Anything GGUF?

It depends on the quant: F16 is 1.3 GB, Q4_0 is 1.6 GB, Q4_0 is 1.6 GB, Q4_0 is 1.6 GB, Q4_0 is 1.6 GB, Q4_0 is 1.6 GB and 24 more.

Where can I download Anything GGUF?

The files are on Hugging Face in the mzwing/Anything-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 Anything on 8 GB VRAM?

Yes, Q4_0 or Q4_1 quantizations use about 2.3 GB memory at 8k context, fitting within 8 GB VRAM.

What is the model size in GGUF?

File sizes range from 1.28 GB (F16) to 2.13 GB (F16).

Does Anything support vision?

No, the model has no vision capabilities.

Similar models

Browse all →

More from mzwing

All by mzwing →

More Anything models

All Anything →

Other tiny models

All tiny models →