What are the hardware requirements for Smaug Slerp 30B V0.1?

Smaug Slerp 30B V0.1 requires approximately 60.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smaug Slerp 30B V0.1 and how large is it?

Smaug Slerp 30B V0.1 is developed by liminerity, 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 Smaug Slerp 30B V0.1?

Smaug Slerp 30B V0.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Smaug Slerp 30B V0.1 by liminerity — VRAM 60.4GB, 32K context

Name: Smaug Slerp 30B V0.1
Author: liminerity

Smaug Slerp 30B V0.1 is an open-source language model by liminerity. Features: 30b LLM, VRAM: 60.4GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.11.

Merged Model Abacusai/smaug-72b-v0.1 Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/liminerity/Smaug-slerp-30b-v0.1

Smaug Slerp 30B V0.1 Parameters and Internals

Additional Notes

Smaug-slerpB-v0.1 is a merge of the abacusai/Smaug-72B-v0.1 models using mergekit.

LLM Name	Smaug Slerp 30B V0.1
Repository 🤗	https://huggingface.co/liminerity/Smaug-slerp-30b-v0.1
Merged Model	Yes
Model Size	30b
Required VRAM	60.4 GB
Updated	2026-07-30
Maintainer	liminerity
Model Type	llama
Model Files	1.9 GB: 1-of-36 0.4 GB: 2-of-36 2.5 GB: 3-of-36 1.9 GB: 4-of-36 1.9 GB: 5-of-36 1.6 GB: 6-of-36 1.7 GB: 7-of-36 1.7 GB: 8-of-36 1.9 GB: 9-of-36 1.9 GB: 10-of-36 1.9 GB: 11-of-36 1.6 GB: 12-of-36 1.7 GB: 13-of-36 1.9 GB: 14-of-36 1.9 GB: 15-of-36 1.9 GB: 16-of-36 1.6 GB: 17-of-36 1.7 GB: 18-of-36 1.7 GB: 19-of-36 1.6 GB: 20-of-36 1.7 GB: 21-of-36 1.7 GB: 22-of-36 1.9 GB: 23-of-36 1.9 GB: 24-of-36 1.7 GB: 25-of-36 1.7 GB: 26-of-36 1.7 GB: 27-of-36 1.9 GB: 28-of-36 1.7 GB: 29-of-36 1.7 GB: 30-of-36 1.6 GB: 31-of-36 1.7 GB: 32-of-36 1.7 GB: 33-of-36 0.4 GB: 34-of-36 2.5 GB: 35-of-36 0.0 GB: 36-of-36
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	152064
Torch Data Type	bfloat16

Rank the Smaug Slerp 30B V0.1 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 Smaug Slerp 30B V0.1

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
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
...via Sample With Temperature2.0	4K / 5.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than liminerity/Smaug-slerp-30b-v0.1.