What are the hardware requirements for 13B Legerdemain L2?

13B Legerdemain L2 requires approximately 52 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed 13B Legerdemain L2 and how large is it?

13B Legerdemain L2 is developed by CalderaAI, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does 13B Legerdemain L2 perform on standard benchmarks?

13B Legerdemain L2 has the following published scores: MMLU 56. Compare against reference models on this page or on the LLM Explorer leaderboards.

13B Legerdemain L2 by CalderaAI — VRAM 52GB, 4K context

Name: 13B Legerdemain L2
Author: CalderaAI

13B Legerdemain L2 is an open-source language model by CalderaAI. Features: 13b LLM, VRAM: 52GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.1, Arc: 61.3, HellaSwag: 83.3, MMLU: 56, GSM8K: 13.

Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/CalderaAI/13B-Legerdemain-L2

13B Legerdemain L2 Parameters and Internals

Model Type

text generation

Use Cases

Primary Use Cases:

Following instructions, specifically Alpaca instructions

Additional Notes

Model merge of 13B-Nous-Hermes by NousResearch and 13B-orca-8k-3319 by OpenAssistant using Model-REVOLVER. Attempted to undermine censorship parts of the network.

Training Details

Methodology:

Model-REVOLVER (Rapid Evolution Via Optimized-List Viewer Evaluated Response). Per-layer merging between parent models.

LLM Name	13B Legerdemain L2
Repository 🤗	https://huggingface.co/CalderaAI/13B-Legerdemain-L2
Model Size	13b
Required VRAM	52 GB
Updated	2026-09-13
Maintainer	CalderaAI
Model Type	llama
Model Files	18.8 GB: 1-of-3 18.8 GB: 2-of-3 14.4 GB: 3-of-3
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.30.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float32

Rank the 13B Legerdemain L2 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 13B Legerdemain L2

Model	Likes	Downloads	VRAM
13B Legerdemain L2 GGUF	2	193	5 GB
13B Legerdemain L2 AWQ	1	6	7 GB
13B Legerdemain L2 GGML	6	3	5 GB
13B Legerdemain L2 GPTQ	4	5	7 GB

Best Alternatives to 13B Legerdemain L2

Best Alternatives	Context / RAM	Downloads	Likes
Luminaura RP 13B	128K / 26 GB	9	1
Yarn Llama 2 13B 128K	128K / 26 GB	184	113
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	5	0
LongAlign 13B 64K	64K / 26 GB	96	13
LongAlign 13B 64K Base	64K / 26 GB	89	3
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	4	4
Openbuddy Llama2 13b64k V15	64K / 26.1 GB	12	2

Note: green Score (e.g. "73.2") means that the model is better than CalderaAI/13B-Legerdemain-L2.