LL

chinese llama 2 13b

LlamaGGUF by hflUpdated 2024-01-24
Download on Hugging Face
Parameters13.3B
Context4K
Layers40
Architecturellama
Smallest quant5.0 GB
Quick answer

chinese llama 2 13b needs about 15.2 GB of memory at Q4_K (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 5.0 GB (Q2_K) to 26.5 GB (F16).

Chinese LLaMA‑2 13B, 13.3B parameters, 4096‑token context

Chinese LLaMA‑2 13B is a 13.3‑billion‑parameter Llama model with a 4096‑token context window. It is available in multiple GGUF quantizations and licensed under Apache‑2.0. The model supports coding tasks and is compatible with llama.cpp.

Good at

  • Coding in Chinese
  • Chinese language generation
  • LLM inference with llama.cpp

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • License is Apache‑2.0

Best for

  • Chatbots in Chinese
  • Code generation in Chinese
  • Local inference on moderate GPUs

Who it’s for. Developers needing a Chinese‑focused Llama model for local deployment. The model is suitable for projects that require coding support and can run on systems with sufficient VRAM to accommodate the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.0 GB 8.8 GB
Too big Get file →
Q2_K5.6 GB 9.4 GB
Too big Get file →
Q3_K6.5 GB 10.3 GB
Too big Get file →
Q3_K6.5 GB 10.3 GB
Too big Get file →
Q4_07.5 GB 11.4 GB
Too big Get file →
Q4_K8.0 GB 11.9 GB
Too big Get file →
Q4_K8.0 GB 11.9 GB
Too big Get file →
Q5_09.2 GB 13.0 GB
Too big Get file →
Q5_K9.4 GB 13.3 GB
Too big Get file →
Q5_K9.4 GB 13.3 GB
Too big Get file →
Q6_K10.9 GB 14.7 GB
Too big Get file →
Q6_K10.9 GB 14.7 GB
Too big Get file →
Q8_014.1 GB 17.9 GB
Too big Get file →
F1626.5 GB 30.4 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 (7.53 GB file, ~14.7 GB memory). For 12‑GB VRAM, Q4_K (8.03 GB file, ~15.2 GB memory). For 16‑GB VRAM, Q5_K (9.41 GB file, ~16.6 GB memory). Estimates are approximate.

What GPU do you need for chinese llama 2 13b?

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: the best quant that fits is Q4_K (8.0 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 21.3 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (26.5 GB file, about 33.7 GB in use).

Which chinese llama 2 13b quant should you choose?

Q4_K (8.0 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 5.0 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
Parameters13.3B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byhfl
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,163
Last updated2024-01-24

Frequently asked questions about chinese llama 2 13b

How much VRAM does chinese llama 2 13b need?

About 15.2 GB at Q4_K with an 8K context window. That is the 8.0 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 chinese llama 2 13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of chinese llama 2 13b GGUF?

It depends on the quant: Q2_K is 5.0 GB, Q2_K is 5.6 GB, Q3_K is 6.5 GB, Q3_K is 6.5 GB, Q4_0 is 7.5 GB, Q4_K is 8.0 GB and 8 more.

What context length does chinese llama 2 13b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download chinese llama 2 13b GGUF?

The files are on Hugging Face in the hfl/chinese-llama-2-13b-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 13b 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.

Can I run Chinese LLaMA‑2 13B on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 14.7 GB of VRAM at 8‑k context.

Is there a version with higher precision?

The F16 quantization is available, but it requires 33.7 GB of VRAM at 8‑k context.

Does the model support vision tasks?

No, the model does not have vision capabilities.

Similar models

Browse all →

More from hfl

All by hfl →

More Llama models

All Llama →

Other medium models

All medium models →