PL

9b plus tie13

PlusGGUF by AryanneUpdated 2024-01-19
Download on Hugging Face
Parameters8.99B
Context32K
Layers40
Architecturellama
Smallest quant5.1 GB
Quick answer

9b plus tie13 needs about 7.0 GB of memory at Q4_K_S (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 5.1 GB (Q4_K_S) to 5.1 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

9b plus tie13 is a 8.99B-parameter Plus model in GGUF format, quantized by Aryanne. Its trained context length is 32K tokens. The repository has 3 quant files, from 5.1 GB (Q4_K_S) to 5.1 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S5.1 GB 7.0 GB
Fits Get file →
Q4_K_S5.1 GB 7.0 GB
Fits Get file →
Q4_K_S5.1 GB 7.0 GB
Fits Get file →

What GPU do you need for 9b plus tie13?

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: the best quant that fits is Q4_K_S (5.1 GB file, about 7.0 GB in use).

Which 9b plus tie13 quant should you choose?

Q4_K_S (5.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_K_S at 5.1 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters8.99B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byAryanne
FamilyPlus
Downloads (HF)47
Last updated2024-01-19

Frequently asked questions about 9b plus tie13

How much VRAM does 9b plus tie13 need?

About 7.0 GB at Q4_K_S with an 8K context window. That is the 5.1 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 9b plus tie13 on an 8 GB GPU?

Yes, with Q4_K_S: the 5.1 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 9b plus tie13 GGUF?

It depends on the quant: Q4_K_S is 5.1 GB, Q4_K_S is 5.1 GB, Q4_K_S is 5.1 GB.

What context length does 9b plus tie13 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download 9b plus tie13 GGUF?

The files are on Hugging Face in the Aryanne/9b_plus_tie13 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 Aryanne

All by Aryanne →

More Plus models

All Plus →

Other small models

All small models →