What are the hardware requirements for 30B Lazarus?

30B Lazarus requires approximately 65.2 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 and how large is it?

30B Lazarus is developed by CalderaAI, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does 30B Lazarus perform on standard benchmarks?

30B Lazarus has the following published scores: MMLU 56.47. Compare against reference models on this page or on the LLM Explorer leaderboards.

30B Lazarus by CalderaAI — VRAM 65.2GB, 2K context

Name: 30B Lazarus
Author: CalderaAI

30B Lazarus is an open-source language model by CalderaAI. Features: 30b LLM, VRAM: 65.2GB, Context: 2K, LLM Explorer Score: 0.1, Arc: 64.9, HellaSwag: 84.3, MMLU: 56.5, GSM8K: 7.7.

Alpaca Cot Endpoints compatible Llama Merge Mix Pytorch Region:us Safetensors Sharded Tensorflow Uncensored Vicuna

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

30B Lazarus Parameters and Internals

Model Type

Language Model

Additional Notes

This model is a result of experimental LoRA applications and model merges. Desired features are applied without diminishing the model's behavior. Limitations include potential intercompetition of LoRAs. Instruct and setup suggestions include Alpaca instruct as primary and Vicuna instruct format as secondary. Various presets in tools like KoboldAI or Text-Generation-WebUI can lead to different outcomes.

LLM Name	30B Lazarus
Repository 🤗	https://huggingface.co/CalderaAI/30B-Lazarus
Model Size	30b
Required VRAM	65.2 GB
Updated	2026-08-22
Maintainer	CalderaAI
Model Type	llama
Model Files	9.8 GB: 1-of-7 10.0 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 10.0 GB: 6-of-7 5.7 GB: 7-of-7 9.8 GB: 1-of-7 10.0 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 10.0 GB: 6-of-7 5.7 GB: 7-of-7
Model Architecture	LlamaForCausalLM
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 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

Quantized Models of the 30B Lazarus

Model	Likes	Downloads	VRAM
30B Lazarus GGUF	1	212	13 GB
30B Lazarus AWQ	4	8	17 GB

Best Alternatives to 30B Lazarus

Best Alternatives	Context / RAM	Downloads	Likes
TildeOpen 30B	64K / 60.9 GB	4576	165
TildeOpen 30B 64K	64K / 60.9 GB	702	3
Tildeopen 30B Mu Instruct	64K / 60.9 GB	41	6
Flash Llama 30M 20001	32K / 0.1 GB	134	0
Smaug Slerp 30B V0.1	32K / 60.4 GB	79	0
Tenebra 30B Alpha01	16K / 65 GB	50	16
Llama33b 16K	16K / 65.2 GB	1	1
Veyra2 Mango 30M Base	4K / 0.1 GB	0	5
Yayi2 30B Llama	4K / 121.2 GB	922	22
... Tokens By Perplexity Bottom K	4K / 5.4 GB	8	0

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