MO

moe merged model auto qtz v0

MoeGGUF by vrathi101Updated 2024-07-02
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant25.8 GB
Quick answer

moe merged model auto qtz v0 needs about 27.3 GB of memory at its main file (a 25.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

moe merged model auto qtz v0 is a 12.9B-parameter Moe model in GGUF format, quantized by vrathi101. Its trained context length is 32K tokens. The repository has 1 quant file, from 25.8 GB to 25.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—25.8 GB 27.3 GB
Too big Get file →

What GPU do you need for moe merged model auto qtz v0?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (25.8 GB file, about 27.3 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byvrathi101
FamilyMoe
Downloads (HF)4
Last updated2024-07-02

Frequently asked questions about moe merged model auto qtz v0

How much VRAM does moe merged model auto qtz v0 need?

About 27.3 GB at its main file with an 8K context window. That is the 25.8 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 moe merged model auto qtz v0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of moe merged model auto qtz v0 GGUF?

It depends on the quant: file is 25.8 GB.

What context length does moe merged model auto qtz v0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download moe merged model auto qtz v0 GGUF?

The files are on Hugging Face in the vrathi101/moe-merged-model-auto_qtz-v0.gguf 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 vrathi101

All by vrathi101 →

More Moe models

All Moe →

Other medium models

All medium models →