PL

Plamo 13b Instruct Nc

PlamoGGUF by RichardErkhovUpdated 2024-07-25
Download on Hugging Face
Parameters13.1B
Context4K
Layers40
Architectureplamo
Smallest quant4.9 GB
Quick answer

Plamo 13b Instruct Nc needs about 7.1 GB of memory at IQ3_S (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 4.9 GB (Q2_K) to 6.4 GB (Q3_K_M).

Plamo 13b Instruct Nc is a 13.1B-parameter Plamo model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 7 quant files, from 4.9 GB (Q2_K) to 6.4 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 5.8 GB
Fits Get file →
IQ3_XS5.5 GB 6.4 GB
Fits Get file →
Q3_K_S5.7 GB 6.7 GB
Fits Get file →
IQ3_S5.7 GB 6.7 GB
Fits Get file →
IQ3_M5.9 GB 6.9 GB
Fits Get file →
Q3_K6.4 GB 7.3 GB
Tight Get file →
Q3_K_M6.4 GB 7.3 GB
Tight Get file →

What GPU do you need for Plamo 13b Instruct Nc?

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 Q3_K (6.4 GB file, about 7.7 GB in use).

Which Plamo 13b Instruct Nc quant should you choose?

IQ3_S (5.7 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 Q2_K at 4.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureplamo
Parameters13.1B
Layers40
Trained context4,096 tokens
KV cache (fp16)100 KB per token

Source

Quantized byRichardErkhov
FamilyPlamo
Downloads (HF)36
Last updated2024-07-25

Frequently asked questions about Plamo 13b Instruct Nc

How much VRAM does Plamo 13b Instruct Nc need?

About 7.1 GB at IQ3_S with an 8K context window. That is the 5.7 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 Plamo 13b Instruct Nc on an 8 GB GPU?

Yes, with Q3_K: the 6.4 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Plamo 13b Instruct Nc GGUF?

It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.5 GB, Q3_K_S is 5.7 GB, IQ3_S is 5.7 GB, IQ3_M is 5.9 GB, Q3_K is 6.4 GB and 1 more.

What context length does Plamo 13b Instruct Nc support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.4 GB at 4K.

Where can I download Plamo 13b Instruct Nc GGUF?

The files are on Hugging Face in the RichardErkhov/pfnet_-_plamo-13b-instruct-nc-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 Plamo 13b Instruct Nc use?

Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Plamo models

All Plamo →

Other medium models

All medium models →