YI

Yi 6B Open Orca

YiGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters6.06B
Context4K
Layers32
Architecturellama
Smallest quant2.6 GB
Quick answer

Yi 6B Open Orca needs about 5.0 GB of memory at Q4_K_M (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 16 quants, from 2.6 GB (Q2_K) to 6.7 GB (Q8_0).

Yi 6B Open Orca is a 6.06B-parameter Yi model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 16 quant files, from 2.6 GB (Q2_K) to 6.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.6 GB 3.4 GB
Fits Get file →
IQ3_XS2.9 GB 3.7 GB
Fits Get file →
Q3_K_S3.0 GB 3.8 GB
Fits Get file →
IQ3_S3.0 GB 3.8 GB
Fits Get file →
IQ3_M3.1 GB 3.9 GB
Fits Get file →
Q3_K_M3.3 GB 4.1 GB
Fits Get file →
Q3_K_L3.5 GB 4.3 GB
Fits Get file →
IQ4_XS3.6 GB 4.4 GB
Fits Get file →
Q4_03.8 GB 4.6 GB
Fits Get file →
Q4_K_S3.8 GB 4.6 GB
Fits Get file →
IQ4_NL3.8 GB 4.6 GB
Fits Get file →
Q4_K_M4.0 GB 4.8 GB
Fits Get file →
Q5_K_S4.5 GB 5.3 GB
Fits Get file →
Q5_K_M4.6 GB 5.4 GB
Fits Get file →
Q6_K5.3 GB 6.1 GB
Fits Get file →
Q8_06.7 GB 7.5 GB
Tight Get file →

What GPU do you need for Yi 6B Open Orca?

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: the best quant that fits is IQ3_XS (2.9 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.6 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.7 GB file, about 7.7 GB in use).

Which Yi 6B Open Orca quant should you choose?

Q4_K_M is the usual starting point for Yi 6B Open Orca: it balances file size and quality well. Here it is a 4.0 GB file.

The Q8_0 file is 6.7 GB, about 1.7 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 2.6 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
Parameters6.06B
Layers32
Trained context4,096 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymradermacher
FamilyYi
Licenseapache-2.0
Downloads (HF)78
Last updated2024-05-06

Frequently asked questions about Yi 6B Open Orca

How much VRAM does Yi 6B Open Orca need?

About 5.0 GB at Q4_K_M with an 8K context window. That is the 4.0 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 6B Open Orca on an 8 GB GPU?

Yes, with Q8_0: the 6.7 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Yi 6B Open Orca GGUF?

It depends on the quant: Q2_K is 2.6 GB, IQ3_XS is 2.9 GB, Q3_K_S is 3.0 GB, IQ3_S is 3.0 GB, IQ3_M is 3.1 GB, Q3_K_M is 3.3 GB and 10 more.

What context length does Yi 6B Open Orca support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.3 GB at 4K.

Where can I download Yi 6B Open Orca GGUF?

The files are on Hugging Face in the mradermacher/Yi-6B_Open-Orca-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 Yi 6B Open Orca use?

Hugging Face lists the license as apache-2.0. 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 mradermacher

All by mradermacher →

More Yi models

All Yi →

Other small models

All small models →