What are the hardware requirements for 30B Lazarus AWQ?

30B Lazarus AWQ requires approximately 17.6 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 30B Lazarus AWQ and how large is it?

30B Lazarus AWQ is developed by TheBloke, a model with 30b 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 30B Lazarus AWQ?

30B Lazarus AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

30B Lazarus AWQ by TheBloke — VRAM 17.6GB, 2K context

Name: 30B Lazarus AWQ
Author: TheBloke

30B Lazarus AWQ is an open-source language model by TheBloke. Features: 30b LLM, VRAM: 17.6GB, Context: 2K, License: other, Quantized, LLM Explorer Score: 0.09.

4-bit Alpaca Awq Base model:calderaai/30b-lazar... Base model:quantized:calderaai... Cot Llama Merge Mix Quantized Region:us Safetensors Sharded Tensorflow Uncensored Vicuna

Model Card on HF 🤗: https://huggingface.co/TheBloke/30B-Lazarus-AWQ

30B Lazarus AWQ Parameters and Internals

Model Type

llama

Additional Notes

Instruct and Setup Suggestions: Alpaca instruct is primary, Vicuna instruct format may work.

Training Details

Data Sources:

wikitext, manticore-30b-chat-pyg-alpha, SuperCOT-LoRA, Storytelling-LLaMa-LoRA, SuperHOT Prototype, GPT4-Alpaca-LoRA, Vicuna Unlocked LoRA

Methodology:

Experimental use of LoRAs on language models and model merges

Context Length:

4096

Model Architecture:

AWQ 128g models, composite model using LoRAs

Input Output

Input Format:

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:

Performance Tips:

Switching between Godlike and Storywriter presets and adjusting output length + instructions in memory can yield different results.

LLM Name	30B Lazarus AWQ
Repository 🤗	https://huggingface.co/TheBloke/30B-Lazarus-AWQ
Model Name	30B Lazarus
Model Creator	Caldera AI
Base Model(s)	30B Lazarus CalderaAI/30B-Lazarus
Model Size	30b
Required VRAM	17.6 GB
Updated	2026-08-07
Maintainer	TheBloke
Model Type	llama
Model Files	10.0 GB: 1-of-2 7.6 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the 30B Lazarus AWQ 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 30B Lazarus AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Hippogriff 30B Chat AWQ	2K / 17.6 GB	11	1
Platypus 30B AWQ	2K / 17.6 GB	6	2
GPlatty 30B AWQ	2K / 17.6 GB	4	2
30B Epsilon AWQ	2K / 17.6 GB	9	4
...ge Llama 30B Instruct 2048 AWQ	2K / 17.6 GB	3	2
VicUnlocked 30B LoRA AWQ	2K / 17.6 GB	2	2
SuperPlatty 30B AWQ	2K / 17.6 GB	7	0
LLaMA 30B AWQ	0K / 17.6 GB	4	3
Tenebra 30B Alpha01 FP16	16K / 65 GB	1833	9
Tenebra 30B Alpha01 4BIT	16K / 19.4 GB	73	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/30B-Lazarus-AWQ.