YI

Yi 34Bx2 MOE 200K

YiGGUF by cloudyuUpdated 2024-03-25
Download on Hugging Face
Parameters60.8B
Context195K
Layers60
Architecturellama
Smallest quant36.7 GB
Quick answer

Yi 34Bx2 MOE 200K needs about 39.2 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Yi 34Bx2 MOE 200K is a 60.8B-parameter Yi model in GGUF format, quantized by cloudyu. Its trained context length is 195K tokens. The repository has 1 quant file, from 36.7 GB (Q4_K_M) to 36.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M36.7 GB 39.2 GB
Too big Get file →

What GPU do you need for Yi 34Bx2 MOE 200K?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (36.7 GB file, about 39.2 GB in use).

Which Yi 34Bx2 MOE 200K quant should you choose?

Q4_K_M is the usual starting point for Yi 34Bx2 MOE 200K: it balances file size and quality well. Here it is a 36.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters60.8B (approximate, mixture of experts)
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bycloudyu
FamilyYi
Downloads (HF)20
Last updated2024-03-25

Frequently asked questions about Yi 34Bx2 MOE 200K

How much VRAM does Yi 34Bx2 MOE 200K need?

About 39.2 GB at Q4_K_M with an 8K context window. That is the 36.7 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 Yi 34Bx2 MOE 200K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 39.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yi 34Bx2 MOE 200K GGUF?

It depends on the quant: Q4_K_M is 36.7 GB.

What context length does Yi 34Bx2 MOE 200K support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Yi 34Bx2 MOE 200K GGUF?

The files are on Hugging Face in the cloudyu/Yi-34Bx2-MOE-200K-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 cloudyu

All by cloudyu →

More Yi models

All Yi →

Other large models

All large models →