DI

DISC LawLLM

DiscGGUF by mradermacherUpdated 2025-02-10
Download on Hugging Face
Parameters13.3B
Context4K
Layers40
Architecturebaichuan
Smallest quant5.4 GB
Quick answer

DISC LawLLM needs about 15.8 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 5.4 GB (Q2_K) to 14.1 GB (Q8_0).

DISC LawLLM – 13.3B Baichuan model for Chinese legal tasks

DISC LawLLM is a 13.3B parameter Baichuan model fine‑tuned for Chinese legal domain. It supports legal text extraction, judgment prediction, summarization, and question answering. The model is released under apache-2.0.

Good at

  • Legal information extraction
  • Judgment prediction
  • Legal question answering

Limits

  • No vision support
  • Requires 8k context for full functionality
  • License is apache-2.0

Best for

  • Legal document summarization
  • Court case classification
  • Legal consultation services

Who it’s for. Developers building Chinese legal AI applications. Researchers needing a specialized legal language model. Legal professionals exploring AI assistance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.2 GB
Too big Get file →
Q3_K_S6.2 GB 10.1 GB
Too big Get file →
Q3_K_M6.8 GB 10.7 GB
Too big Get file →
Q3_K_L7.3 GB 11.1 GB
Too big Get file →
IQ4_XS7.3 GB 11.2 GB
Too big Get file →
Q4_K_S7.9 GB 11.8 GB
Too big Get file →
Q4_K_M8.6 GB 12.4 GB
Too big Get file →
Q5_K_S9.3 GB 13.2 GB
Too big Get file →
Q5_K_M9.8 GB 13.7 GB
Too big Get file →
Q6_K11.6 GB 15.4 GB
Too big Get file →
Q8_014.1 GB 18.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (7.93 GB file, ~15.1 GB memory). For 12 GB VRAM, use Q5_K_S (9.34 GB file, ~16.6 GB memory). For 16 GB VRAM, use Q6_K (11.56 GB file, ~18.8 GB memory). Estimates are approximate.

What GPU do you need for DISC LawLLM?

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 (8.6 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 21.3 GB in use).

Which DISC LawLLM quant should you choose?

Q4_K_M is the usual starting point for DISC LawLLM: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 14.1 GB, about 1.6 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 5.4 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

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

Source

Quantized bymradermacher
FamilyDisc
Licenseapache-2.0
Downloads (HF)1,738
Last updated2025-02-10

Frequently asked questions about DISC LawLLM

How much VRAM does DISC LawLLM need?

About 15.8 GB at Q4_K_M with an 8K context window. That is the 8.6 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 DISC LawLLM on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DISC LawLLM GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 6.2 GB, Q3_K_M is 6.8 GB, Q3_K_L is 7.3 GB, IQ4_XS is 7.3 GB, Q4_K_S is 7.9 GB and 5 more.

What context length does DISC LawLLM 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 DISC LawLLM GGUF?

The files are on Hugging Face in the mradermacher/DISC-LawLLM-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 DISC LawLLM 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 DISC LawLLM on 8 GB VRAM?

Use the Q4_K_S quant, which is 7.93 GB and requires about 15.1 GB memory at 8k context.

Does DISC LawLLM support English legal text?

The model is specialized for Chinese legal domain; English support is not guaranteed.

Is DISC LawLLM free to use?

Yes, it is released under the apache-2.0 license.

Other GGUFs of DISC-LawLLM

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Disc models

All Disc →

Other medium models

All medium models →