LL

Ziya Llama 13b Medical Merged

LlamaGGUF by mradermacherUpdated 2024-11-05
Download on Hugging Face
Parameters13.1B
Context2K
Layers40
Architecturellama
Smallest quant4.9 GB
Quick answer

Ziya Llama 13b Medical Merged needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 4.9 GB (Q2_K) to 13.9 GB (Q8_0).

Ziya Llama 13b Medical Merged – a 13.1B parameter medical LLaMA model

Ziya Llama 13b Medical Merged is a 13.1B parameter LLaMA model fine‑tuned on 240万条中英文医疗指令数据集. It supports Chinese and English medical Q&A and general instruction following. The model is released under the apache-2.0 license.

Good at

  • Medical Q&A in Chinese and English
  • General instruction following
  • Fine‑tuned medical knowledge

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Requires at least 12.1 GB VRAM for Q2_K at 8k context

Best for

  • Medical chatbot deployments
  • Clinical knowledge assistants
  • Research on bilingual medical NLP

Who it’s for. Developers building medical chat interfaces or research tools that need bilingual medical expertise. The model is suitable for environments with moderate GPU memory and no need for vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 7.1 GB
Fits Get file →
Q3_K_S5.7 GB 7.9 GB
Tight Get file →
Q3_K_M6.4 GB 8.6 GB
Too big Get file →
Q3_K_L7.0 GB 9.2 GB
Too big Get file →
IQ4_XS7.1 GB 9.2 GB
Too big Get file →
Q4_07.4 GB 9.6 GB
Too big Get file →
Q4_K_S7.5 GB 9.7 GB
Too big Get file →
Q4_K_M7.9 GB 10.1 GB
Too big Get file →
Q5_K_S9.0 GB 11.2 GB
Too big Get file →
Q5_K_M9.3 GB 11.5 GB
Too big Get file →
Q6_K10.7 GB 12.9 GB
Too big Get file →
Q8_013.9 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.9 GB, 12.1 GB memory at 8k context). For 12 GB VRAM, Q3_K_S (5.71 GB, 12.9 GB memory). For 16 GB VRAM, Q4_K_M (7.92 GB, 15.1 GB memory). Estimates are approximate.

What GPU do you need for Ziya Llama 13b Medical Merged?

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_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.9 GB file, about 21.1 GB in use).

Which Ziya Llama 13b Medical Merged quant should you choose?

Q4_K_M is the usual starting point for Ziya Llama 13b Medical Merged: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.9 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 4.9 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
Parameters13.1B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,033
Last updated2024-11-05

Frequently asked questions about Ziya Llama 13b Medical Merged

How much VRAM does Ziya Llama 13b Medical Merged need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Ziya Llama 13b Medical Merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ziya Llama 13b Medical Merged GGUF?

It depends on the quant: Q2_K is 4.9 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.4 GB, Q3_K_L is 7.0 GB, IQ4_XS is 7.1 GB, Q4_0 is 7.4 GB and 6 more.

What context length does Ziya Llama 13b Medical Merged support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download Ziya Llama 13b Medical Merged GGUF?

The files are on Hugging Face in the mradermacher/ziya-llama-13b-medical-merged-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 Ziya Llama 13b Medical Merged 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 this model on 8 GB VRAM?

Yes, using the Q2_K quant which requires about 12.1 GB VRAM at 8k context.

Does this model support vision tasks?

No, the model only handles text and has no vision capability.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of ziya-llama-13b-medical-merged

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →