WE

WestLake 10.7B v2

WestlakeGGUF by froggericUpdated 2024-03-12
Download on Hugging Face
Parameters10.7B
Context32K
Layers48
Architecturellama
Smallest quant6.1 GB
Quick answer

WestLake 10.7B v2 needs about 9.5 GB of memory at its main file (a 7.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.1 GB to 11.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

WestLake 10.7B v2 is a 10.7B-parameter Westlake model in GGUF format, quantized by froggeric. Its trained context length is 32K tokens. The repository has 4 quant files, from 6.1 GB to 11.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.1 GB 8.2 GB
Too big Get file →
—7.4 GB 9.5 GB
Too big Get file →
Q6_K8.8 GB 10.9 GB
Too big Get file →
Q8_011.4 GB 13.5 GB
Too big Get file →

What GPU do you need for WestLake 10.7B v2?

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: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which WestLake 10.7B v2 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 6.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byfroggeric
FamilyWestlake
Licenseapache-2.0
Downloads (HF)359
Last updated2024-03-12

Frequently asked questions about WestLake 10.7B v2

How much VRAM does WestLake 10.7B v2 need?

About 9.5 GB at its main file with an 8K context window. That is the 7.4 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 WestLake 10.7B v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WestLake 10.7B v2 GGUF?

It depends on the quant: file is 6.1 GB, file is 7.4 GB, Q6_K is 8.8 GB, Q8_0 is 11.4 GB.

What context length does WestLake 10.7B v2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download WestLake 10.7B v2 GGUF?

The files are on Hugging Face in the froggeric/WestLake-10.7B-v2-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 WestLake 10.7B v2 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.

Other GGUFs of WestLake-7B-v2

Similar models

Browse all →

More from froggeric

All by froggeric →

More Westlake models

All Westlake →

Other medium models

All medium models →