MA

Manticore-13b-Chat-Pyg-Guanaco

ManticoreGGUF by v000000Updated 2024-07-04
Download on Hugging Face
Parameters13B
Context2K
Layers40
Architecturellama
Smallest quant9.2 GB
Quick answer

Manticore-13b-Chat-Pyg-Guanaco needs about 17.9 GB of memory at Q6_K (a 10.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 9.2 GB (Q5_K_M) to 13.8 GB (Q8_0).

Manticore-13b-Chat-Pyg-Guanaco is a 13B-parameter Manticore model in GGUF format, quantized by v000000. Its trained context length is 2K tokens. The repository has 3 quant files, from 9.2 GB (Q5_K_M) to 13.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M9.2 GB 11.4 GB
Too big Get file →
Q6_K10.7 GB 12.9 GB
Too big Get file →
Q8_013.8 GB 16.0 GB
Too big Get file →

What GPU do you need for Manticore-13b-Chat-Pyg-Guanaco?

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: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which Manticore-13b-Chat-Pyg-Guanaco quant should you choose?

Q6_K (10.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_M at 9.2 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized byv000000
FamilyManticore
Downloads (HF)70
Last updated2024-07-04

Frequently asked questions about Manticore-13b-Chat-Pyg-Guanaco

How much VRAM does Manticore-13b-Chat-Pyg-Guanaco need?

About 17.9 GB at Q6_K with an 8K context window. That is the 10.7 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 Manticore-13b-Chat-Pyg-Guanaco on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Manticore-13b-Chat-Pyg-Guanaco GGUF?

It depends on the quant: Q5_K_M is 9.2 GB, Q6_K is 10.7 GB, Q8_0 is 13.8 GB.

What context length does Manticore-13b-Chat-Pyg-Guanaco support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download Manticore-13b-Chat-Pyg-Guanaco GGUF?

The files are on Hugging Face in the v000000/Manticore-13b-Chat-Pyg-Guanaco-GGUFs 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 v000000

All by v000000 →

More Manticore models

All Manticore →

Other medium models

All medium models →