What are the hardware requirements for Law LLM 13B 4.0bpw H6 EXL2?

Law LLM 13B 4.0bpw H6 EXL2 requires approximately 6.8 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Law LLM 13B 4.0bpw H6 EXL2 and how large is it?

Law LLM 13B 4.0bpw H6 EXL2 is developed by LoneStriker, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Law LLM 13B 4.0bpw H6 EXL2?

Law LLM 13B 4.0bpw H6 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Law LLM 13B 4.0bpw H6 EXL2 by LoneStriker — VRAM 6.8GB, 2K context

Name: Law LLM 13B 4.0bpw H6 EXL2
Author: LoneStriker

Law LLM 13B 4.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 13b LLM, VRAM: 6.8GB, Context: 2K, Quantized, Instruction-Based, LLM Explorer Score: 0.1.

Arxiv:2309.09530 Dataset:eleutherai/pile Dataset:gair/lima Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol... En Endpoints compatible Exl2 Instruct Legal Llama Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/LoneStriker/law-LLM-13B-4.0bpw-h6-exl2

Law LLM 13B 4.0bpw H6 EXL2 Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

biomedicine, finance, law

Additional Notes

The reading comprehension approach improves prompting performance for question answering in domain-specific contexts like biomedicine, finance, and law.

Training Details

Data Sources:

Open-Orca/OpenOrca, GAIR/lima, WizardLM/WizardLM_evol_instruct_V2_196k, EleutherAI/pile

Methodology:

Continued pre-training on domain-specific corpora with a reading comprehension approach

Release Notes

Version:

13B

Date:

12/19

Notes:

Released the 13B base models developed from LLaMA-1-13B for law.

Version:

Chat

Date:

12/8

Notes:

Released chat models developed from LLaMA-2-Chat-7B.

Version:

1-7B

Date:

9/18

Notes:

Released paper, code, data, and base models developed from LLaMA-1-7B.

LLM Name	Law LLM 13B 4.0bpw H6 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/law-LLM-13B-4.0bpw-h6-exl2
Model Size	13b
Required VRAM	6.8 GB
Updated	2026-07-21
Maintainer	LoneStriker
Model Type	llama
Instruction-Based	Yes
Model Files	6.8 GB
Supported Languages	en
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Padding Token	<pad>
Unk Token	<unk>
Vocabulary Size	32001
Torch Data Type	float16

Rank the Law LLM 13B 4.0bpw H6 EXL2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Law LLM 13B 4.0bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 13B Instruct Fp16	16K / 26 GB	137	28
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3
...13B Instruct Nf4 Fp16 Upscaled	16K / 26 GB	6	0
Model 007 13b V2	4K / 26 GB	57	4
...B Fast Instruct 4bit Quantized	4K / 7.8 GB	6	0
...igogne2 Enno 13B Sft Lora 4bit	4K / 26 GB	786	0
Xwin LM 13B V0.2 EXL2	4K / 5.2 GB	12	3
Mythalion 13B 2.30bpw H4 EXL2	4K / 4.1 GB	4	3
...lion Kimiko V2.6.05bpw H8 EXL2	4K / 10.1 GB	5	1
Finance LLM 13B 6.0bpw H6 EXL2	2K / 10 GB	5	1

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/law-LLM-13B-4.0bpw-h6-exl2.