LL

chinese llama 2 1.3b

LlamaGGUF by hflUpdated 2024-01-24
Download on Hugging Face
Parameters1.26B
Context4K
Layers4
Architecturellama
Smallest quant0.6 GB
Quick answer

chinese llama 2 1.3b needs about 1.8 GB of memory at Q4_K (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.6 GB (Q2_K) to 2.5 GB (F16).

chinese llama 2 1.3b is a 1.26B-parameter Llama model in GGUF format, quantized by hfl. Its trained context length is 4K tokens. The repository has 14 quant files, from 0.6 GB (Q2_K) to 2.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.6 GB 1.3 GB
Fits Get file →
Q2_K0.6 GB 1.4 GB
Fits Get file →
Q3_K0.7 GB 1.4 GB
Fits Get file →
Q3_K0.7 GB 1.5 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_K0.8 GB 1.6 GB
Fits Get file →
Q4_K0.8 GB 1.6 GB
Fits Get file →
Q5_00.9 GB 1.7 GB
Fits Get file →
Q5_K0.9 GB 1.7 GB
Fits Get file →
Q5_K0.9 GB 1.7 GB
Fits Get file →
Q6_K1.0 GB 1.8 GB
Fits Get file →
Q6_K1.0 GB 1.8 GB
Fits Get file →
Q8_01.3 GB 2.1 GB
Fits Get file →
F162.5 GB 3.3 GB
Fits Get file →

What GPU do you need for chinese llama 2 1.3b?

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 F16 (2.5 GB file, about 3.6 GB in use).

Which chinese llama 2 1.3b quant should you choose?

Q4_K (0.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 0.6 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
Parameters1.26B
Layers4
Trained context4,096 tokens
KV cache (fp16)64 KB per token

Source

Quantized byhfl
FamilyLlama
Licenseapache-2.0
Downloads (HF)550
Last updated2024-01-24

Frequently asked questions about chinese llama 2 1.3b

How much VRAM does chinese llama 2 1.3b need?

About 1.8 GB at Q4_K with an 8K context window. That is the 0.8 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 chinese llama 2 1.3b on an 8 GB GPU?

Yes, with F16: the 2.5 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of chinese llama 2 1.3b GGUF?

It depends on the quant: Q2_K is 0.6 GB, Q2_K is 0.6 GB, Q3_K is 0.7 GB, Q3_K is 0.7 GB, Q4_0 is 0.8 GB, Q4_K is 0.8 GB and 8 more.

What context length does chinese llama 2 1.3b 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 chinese llama 2 1.3b GGUF?

The files are on Hugging Face in the hfl/chinese-llama-2-1.3b-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 chinese llama 2 1.3b 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 hfl

All by hfl →

More Llama models

All Llama →

Other tiny models

All tiny models →