YI

Yi-1.5-34B-32K

YiGGUF by redponikeUpdated 2024-05-20
Download on Hugging Face
Parameters34.4B
Context32K
Layers60
Architecturellama
Smallest quant15.0 GB
Quick answer

Yi-1.5-34B-32K needs about 19.2 GB of memory at Q3_K_M (a 16.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 15.0 GB (Q3_K_S) to 19.6 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Yi-1.5-34B-32K is a 34.4B-parameter Yi model in GGUF format, quantized by redponike. Its trained context length is 32K tokens. The repository has 3 quant files, from 15.0 GB (Q3_K_S) to 19.6 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q4_K_S19.6 GB 22.1 GB
Too big Get file →

What GPU do you need for Yi-1.5-34B-32K?

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_S (19.6 GB file, about 22.1 GB in use).

Which Yi-1.5-34B-32K quant should you choose?

Q3_K_M (16.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q3_K_S at 15.0 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
Parameters34.4B
Layers60
Trained context32,768 tokens
KV cache (fp16)240 KB per token

Source

Quantized byredponike
FamilyYi
Downloads (HF)102
Last updated2024-05-20

Frequently asked questions about Yi-1.5-34B-32K

How much VRAM does Yi-1.5-34B-32K need?

About 19.2 GB at Q3_K_M with an 8K context window. That is the 16.7 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-1.5-34B-32K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yi-1.5-34B-32K GGUF?

It depends on the quant: Q3_K_S is 15.0 GB, Q3_K_M is 16.7 GB, Q4_K_S is 19.6 GB.

What context length does Yi-1.5-34B-32K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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-1.5-34B-32K GGUF?

The files are on Hugging Face in the redponike/Yi-1.5-34B-32K-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 redponike

All by redponike →

More Yi models

All Yi →

Other large models

All large models →