LL

Llama 3 Taiwan 70B Instruct

LlamaGGUF by chienweichangUpdated 2024-07-12
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Llama 3 Taiwan 70B Instruct needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 13 quants, from 26.4 GB (Q2_K) to 141.1 GB (F16).

Llama 3 Taiwan 70B Instruct – 70B parameter model for Traditional Mandarin and English

Llama 3 Taiwan 70B Instruct is a 70B parameter model finetuned on Traditional Mandarin and English data. It supports 8K context length and is released under the llama3 license. The model is available in GGUF format with multiple quantizations.

Good at

  • Traditional Mandarin language tasks
  • English instruction following
  • Long‑form dialogue up to 8K tokens

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License restricts commercial redistribution

Best for

  • Chatbots for Taiwanese users
  • Industry knowledge queries in legal and medical domains
  • Educational content generation in Traditional Mandarin

Who it’s for. Developers building chat interfaces for Taiwanese audiences or multilingual applications needing strong Mandarin support. Researchers needing a large‑scale model for fine‑tuning on domain data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
Q4_040.0 GB 43.2 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q4_144.3 GB 47.5 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →
F16141.1 GB (3 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M or Q4_K_S (≈45 GB memory at 8K context). For 16 GB VRAM use Q3_K_M or Q3_K_L. For 32 GB VRAM use Q4_0 or Q4_1. Full precision (F16) requires 144 GB memory and is only feasible on high‑end GPUs.

What GPU do you need for Llama 3 Taiwan 70B Instruct?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).

Which Llama 3 Taiwan 70B Instruct quant should you choose?

Q4_K_M is the usual starting point for Llama 3 Taiwan 70B Instruct: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 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 26.4 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
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bychienweichang
FamilyLlama
Licensellama3
Downloads (HF)718
Last updated2024-07-12

Frequently asked questions about Llama 3 Taiwan 70B Instruct

How much VRAM does Llama 3 Taiwan 70B Instruct need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Llama 3 Taiwan 70B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3 Taiwan 70B Instruct GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_L is 37.1 GB, Q4_0 is 40.0 GB, Q4_K_S is 40.3 GB and 7 more.

What context length does Llama 3 Taiwan 70B Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Llama 3 Taiwan 70B Instruct GGUF?

The files are on Hugging Face in the chienweichang/Llama-3-Taiwan-70B-Instruct-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 Llama 3 Taiwan 70B Instruct use?

Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

No, the smallest quantization requires at least 29.6 GB memory at 8K context. 8 GB VRAM is insufficient.

Does the model support image input?

No, the model has no vision capabilities.

Is the model licensed for commercial use?

The model is released under the llama3 license, which restricts commercial redistribution.

Other GGUFs of Llama-3-Taiwan-70B-Instruct

Similar models

Browse all →

More from chienweichang

All by chienweichang →

More Llama models

All Llama →

Other large models

All large models →