PI

PiVoT MoE

PivotGGUF by maywellUpdated 2023-12-16
Download on Hugging Face
Parameters36.1B
Context32K
Layers48
Architecturellama
Smallest quant15.7 GB
Quick answer

PiVoT MoE needs about 22.5 GB of memory at Q4_K_M (a 20.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 15.7 GB (Q3_K_M) to 29.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

PiVoT MoE is a 36.1B-parameter Pivot model in GGUF format, quantized by maywell. Its trained context length is 32K tokens. The repository has 4 quant files, from 15.7 GB (Q3_K_M) to 29.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M15.7 GB 17.8 GB
Too big Get file →
Q4_020.3 GB 22.5 GB
Too big Get file →
Q4_K_M20.4 GB 22.5 GB
Too big Get file →
Q6_K29.6 GB 31.7 GB
Too big Get file →

What GPU do you need for PiVoT MoE?

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 Q4_K_M (20.4 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.6 GB file, about 31.7 GB in use).

Which PiVoT MoE quant should you choose?

Q4_K_M is the usual starting point for PiVoT MoE: it balances file size and quality well. Here it is a 20.4 GB file.

If memory is tight, the smallest file is Q3_K_M at 15.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters36.1B (approximate, mixture of experts)
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymaywell
FamilyPivot
Downloads (HF)184
Last updated2023-12-16

Frequently asked questions about PiVoT MoE

How much VRAM does PiVoT MoE need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 20.4 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 PiVoT MoE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PiVoT MoE GGUF?

It depends on the quant: Q3_K_M is 15.7 GB, Q4_0 is 20.3 GB, Q4_K_M is 20.4 GB, Q6_K is 29.6 GB.

What context length does PiVoT MoE support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download PiVoT MoE GGUF?

The files are on Hugging Face in the maywell/PiVoT-MoE-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 PiVoT MoE 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 maywell

All by maywell →

More Pivot models

All Pivot →

Other large models

All large models →