PE

persimmon-8b-chat

PersimmonGGUF by GalunidUpdated 2023-11-06
Download on Hugging Face
Parameters9.4B
Context16K
Layers36
Architecturepersimmon
Smallest quant6.1 GB
Quick answer

persimmon-8b-chat needs about 11.4 GB of memory at Q4_K (a 6.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.

persimmon-8b-chat is a 9.4B-parameter Persimmon model in GGUF format, quantized by Galunid. Its trained context length is 16K tokens. The repository has 1 quant file, from 6.1 GB (Q4_K) to 6.1 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K6.1 GB 11.4 GB
Too big Get file →

What GPU do you need for persimmon-8b-chat?

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: the best quant that fits is Q4_K (6.1 GB file, about 11.4 GB in use).

Which persimmon-8b-chat quant should you choose?

Q4_K (6.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepersimmon
Parameters9.4B
Layers36
Trained context16,384 tokens
KV cache (fp16)576 KB per token

Source

Quantized byGalunid
FamilyPersimmon
Downloads (HF)20
Last updated2023-11-06

Frequently asked questions about persimmon-8b-chat

How much VRAM does persimmon-8b-chat need?

About 11.4 GB at Q4_K with an 8K context window. That is the 6.1 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 persimmon-8b-chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of persimmon-8b-chat GGUF?

It depends on the quant: Q4_K is 6.1 GB.

What context length does persimmon-8b-chat support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.8 GB at 8K and 9.7 GB at 16K.

Where can I download persimmon-8b-chat GGUF?

The files are on Hugging Face in the Galunid/persimmon-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 Galunid

All by Galunid →

More Persimmon models

All Persimmon →

Other small models

All small models →