CH

Chaifighter 20B v3 Q8 0

ChaifighterGGUF by Marcus-ArcadiusUpdated 2024-09-01
Download on Hugging Face
Parameters19.5B
Context4K
Layers88
Architecturellama
Smallest quant20.7 GB
Quick answer

Chaifighter 20B v3 Q8 0 needs about 24.1 GB of memory at Q8_0 (a 20.7 GB file) with an 8K context window, so it fits on a 32 GB GPU.

Chaifighter 20B v3 Q8 0 is a 19.5B-parameter Chaifighter model in GGUF format, quantized by Marcus-Arcadius. Its trained context length is 4K tokens. The repository has 1 quant file, from 20.7 GB (Q8_0) to 20.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_020.7 GB 22.7 GB
Too big Get file →

What GPU do you need for Chaifighter 20B v3 Q8 0?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q8_0 (20.7 GB file, about 24.1 GB in use).

Which Chaifighter 20B v3 Q8 0 quant should you choose?

Q8_0 (20.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters19.5B
Layers88
Trained context4,096 tokens
KV cache (fp16)352 KB per token

Source

Quantized byMarcus-Arcadius
Licenseapache-2.0
Downloads (HF)21
Last updated2024-09-01

Frequently asked questions about Chaifighter 20B v3 Q8 0

How much VRAM does Chaifighter 20B v3 Q8 0 need?

About 24.1 GB at Q8_0 with an 8K context window. That is the 20.7 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 Chaifighter 20B v3 Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Chaifighter 20B v3 Q8 0 GGUF?

It depends on the quant: Q8_0 is 20.7 GB.

What context length does Chaifighter 20B v3 Q8 0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.0 GB at 8K and 1.5 GB at 4K.

Where can I download Chaifighter 20B v3 Q8 0 GGUF?

The files are on Hugging Face in the Marcus-Arcadius/Chaifighter-20B-v3-Q8_0-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 Chaifighter 20B v3 Q8 0 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Chaifighter-20B-v3

Similar models

Browse all →

More from Marcus-Arcadius

All by Marcus-Arcadius →

More Chaifighter models

All Chaifighter →

Other medium models

All medium models →