YI

Fook Yi 34B 32K v1

YiGGUF by BeaverLegacyUpdated 2024-07-22
Download on Hugging Face
Parameters34.4B
Context32K
Layers60
Architecturellama
Smallest quant12.8 GB
Quick answer

Fook Yi 34B 32K v1 needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 12.8 GB (Q2_K) to 36.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Fook Yi 34B 32K v1 is a 34.4B-parameter Yi model in GGUF format, quantized by BeaverLegacy. Its trained context length is 32K tokens. The repository has 6 quant files, from 12.8 GB (Q2_K) to 36.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.8 GB 15.3 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →
Q8_036.5 GB 39.1 GB
Too big Get file →

What GPU do you need for Fook Yi 34B 32K v1?

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 (12.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which Fook Yi 34B 32K v1 quant should you choose?

Q4_K_M is the usual starting point for Fook Yi 34B 32K v1: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 GB, about 1.8 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 12.8 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
Parameters34.4B
Layers60
Trained context32,768 tokens
KV cache (fp16)240 KB per token

Source

Quantized byBeaverLegacy
FamilyYi
Downloads (HF)29
Last updated2024-07-22

Frequently asked questions about Fook Yi 34B 32K v1

How much VRAM does Fook Yi 34B 32K v1 need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 Fook Yi 34B 32K v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Fook Yi 34B 32K v1 GGUF?

It depends on the quant: Q2_K is 12.8 GB, Q3_K_M is 16.7 GB, Q4_K_M is 20.7 GB, Q5_K_M is 24.3 GB, Q6_K is 28.2 GB, Q8_0 is 36.5 GB.

What context length does Fook Yi 34B 32K v1 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 Fook Yi 34B 32K v1 GGUF?

The files are on Hugging Face in the BeaverLegacy/Fook-Yi-34B-32K-v1-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 Fook Yi 34B 32K v1 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 BeaverLegacy

All by BeaverLegacy →

More Yi models

All Yi →

Other large models

All large models →