BU

Bunny v1 0 4B

BunnyGGUF by guinmoonUpdated 2024-10-07
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturephi3
Smallest quant1.6 GB
Quick answer

Bunny v1 0 4B needs about 5.7 GB of memory at Q3_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 1.6 GB (IQ3_XXS) to 2.6 GB (Q5_K_S).

Bunny v1 0 4B is a 3.82B-parameter Bunny model in GGUF format, quantized by guinmoon. Its trained context length is 4K tokens. The repository has 6 quant files, from 1.6 GB (IQ3_XXS) to 2.6 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS1.6 GB 3.7 GB
Fits Get file →
IQ3_M1.9 GB 4.0 GB
Fits Get file →
Q3_K_M2.0 GB 4.1 GB
Fits Get file →
IQ4_XS2.1 GB 4.2 GB
Fits Get file →
Q4_K_S2.2 GB 4.3 GB
Fits Get file →
Q5_K_S2.6 GB 4.8 GB
Fits Get file →

What GPU do you need for Bunny v1 0 4B?

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 Q4_K_S (2.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (2.6 GB file, about 6.4 GB in use).

Which Bunny v1 0 4B quant should you choose?

Q3_K_M (2.0 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.

If memory is tight, the smallest file is IQ3_XXS at 1.6 GB, with the quality trade-offs that come with fewer bits. 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

Architecturephi3
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byguinmoon
FamilyBunny
Downloads (HF)42
Last updated2024-10-07

Frequently asked questions about Bunny v1 0 4B

How much VRAM does Bunny v1 0 4B need?

About 5.7 GB at Q3_K_M with an 8K context window. That is the 2.0 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 Bunny v1 0 4B on an 8 GB GPU?

Yes, with Q5_K_S: the 2.6 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bunny v1 0 4B GGUF?

It depends on the quant: IQ3_XXS is 1.6 GB, IQ3_M is 1.9 GB, Q3_K_M is 2.0 GB, IQ4_XS is 2.1 GB, Q4_K_S is 2.2 GB, Q5_K_S is 2.6 GB.

What context length does Bunny v1 0 4B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download Bunny v1 0 4B GGUF?

The files are on Hugging Face in the guinmoon/Bunny-v1_0-4B-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 guinmoon

All by guinmoon →

More Bunny models

All Bunny →

Other small models

All small models →