PI

maywell_pivot-moe

PivotGGUF by TheBlokeUpdated 2023-12-17
Download on Hugging Face
Parameters36B
Context32K
Layers48
Architecturellama
Smallest quant12.0 GB
Quick answer

maywell_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 8 quants, from 12.0 GB (Q2_K) to 38.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

36B Mixture of Experts model for roleplaying

maywell_pivot-moe is a 36B parameter Mixture of Experts model based on Pivot. It is trained with a 32768 token context window and is optimized for roleplaying scenarios. The model is released under a cc‑by‑nc‑4.0 license.

Good at

  • Roleplaying with diverse characters
  • Dynamic expert selection
  • Large context handling

Limits

  • No vision support
  • Requires GPU for efficient inference
  • cc‑by‑nc‑4.0 license limits commercial use

Best for

  • Interactive storytelling
  • Character dialogue generation
  • Creative writing assistance

Who it’s for. Developers and hobbyists who need a roleplaying AI with a large context window and flexible expert mixing. The model is suitable for non‑commercial projects that can run on GPU‑enabled hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.0 GB 14.1 GB
Too big Get file →
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 →
Q5_024.8 GB 27.0 GB
Too big Get file →
Q5_K_M24.9 GB 27.0 GB
Too big Get file →
Q6_K29.6 GB 31.7 GB
Too big Get file →
Q8_038.4 GB 40.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (12.02 GB file, 14.1 GB memory at 8 k context). If 16 GB VRAM is available, Q4_K_M (20.37 GB file, 22.5 GB memory) is a good balance. For 32 GB VRAM, Q6_K (29.62 GB file, 31.7 GB memory) or Q8_0 (38.36 GB file, 40.5 GB memory) can be used.

What GPU do you need for maywell_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: the best quant that fits is Q2_K (12.0 GB file, about 14.1 GB in use).
  • 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).
  • 48 GB VRAM: the best quant that fits is Q8_0 (38.4 GB file, about 40.5 GB in use).

Which maywell_pivot-moe quant should you choose?

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

The Q8_0 file is 38.4 GB, about 1.9 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 12.0 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

Architecturellama
Parameters36B (approximate, mixture of experts)
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilyPivot
Downloads (HF)1,411
Last updated2023-12-17

Frequently asked questions about maywell_pivot-moe

How much VRAM does maywell_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 maywell_pivot-moe on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of maywell_pivot-moe GGUF?

It depends on the quant: Q2_K is 12.0 GB, Q3_K_M is 15.7 GB, Q4_0 is 20.3 GB, Q4_K_M is 20.4 GB, Q5_0 is 24.8 GB, Q5_K_M is 24.9 GB and 2 more.

What context length does maywell_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 maywell_pivot-moe GGUF?

The files are on Hugging Face in the TheBloke/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 maywell_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.

Can I run this model on 8 GB VRAM?

Yes, the Q2_K quantization requires 12.02 GB file size and approximately 14.1 GB memory at 8 k context, which fits within 8 GB VRAM with efficient batching.

Does this model support vision tasks?

No, the model has no vision capabilities and is designed solely for text generation.

Is this model suitable for commercial use?

No, the cc‑by‑nc‑4.0 license prohibits commercial use without permission.

Other GGUFs of PiVoT-MoE

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Pivot models

All Pivot →

Other large models

All large models →