TA

Taiwan LLM 8x7B DPO

TaiwanGGUF by ZoneTwelveUpdated 2024-04-17
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

Taiwan LLM 8x7B DPO needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 10 quants, from 17.3 GB (Q2_K) to 33.2 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Taiwan LLM 8x7B DPO is a 46.7B-parameter Taiwan model in GGUF format, quantized by ZoneTwelve. Its trained context length is 32K tokens. The repository has 10 quant files, from 17.3 GB (Q2_K) to 33.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB (23 parts) 18.9 GB
Too big Get file →
Q3_K_S20.4 GB (108 parts) 22.0 GB
Too big Get file →
Q3_K_M22.5 GB (108 parts) 24.1 GB
Too big Get file →
Q3_K_L24.2 GB (106 parts) 25.7 GB
Too big Get file →
Q4_026.4 GB (108 parts) 28.0 GB
Too big Get file →
Q4_K_S26.7 GB (109 parts) 28.3 GB
Too big Get file →
Q4_K_M28.4 GB (109 parts) 30.0 GB
Too big Get file →
Q5_032.2 GB (110 parts) 33.8 GB
Too big Get file →
Q5_K_S32.2 GB (110 parts) 33.8 GB
Too big Get file →
Q5_K_M33.2 GB (110 parts) 34.8 GB
Too big Get file →

What GPU do you need for Taiwan LLM 8x7B DPO?

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 Q3_K_S (20.4 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (33.2 GB file, about 34.8 GB in use).

Which Taiwan LLM 8x7B DPO quant should you choose?

Q4_K_M is the usual starting point for Taiwan LLM 8x7B DPO: it balances file size and quality well. Here it is a 28.4 GB file.

If memory is tight, the smallest file is Q2_K at 17.3 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
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byZoneTwelve
FamilyTaiwan
Licenseapache-2.0
Downloads (HF)85
Last updated2024-04-17

Frequently asked questions about Taiwan LLM 8x7B DPO

How much VRAM does Taiwan LLM 8x7B DPO need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 Taiwan LLM 8x7B DPO on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Taiwan LLM 8x7B DPO GGUF?

It depends on the quant: Q2_K is 17.3 GB, Q3_K_S is 20.4 GB, Q3_K_M is 22.5 GB, Q3_K_L is 24.2 GB, Q4_0 is 26.4 GB, Q4_K_S is 26.7 GB and 4 more.

What context length does Taiwan LLM 8x7B DPO support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Taiwan LLM 8x7B DPO GGUF?

The files are on Hugging Face in the ZoneTwelve/Taiwan-LLM-8x7B-DPO-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 Taiwan LLM 8x7B DPO 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 ZoneTwelve

All by ZoneTwelve →

More Taiwan models

All Taiwan →

Other large models

All large models →