What are the hardware requirements for Llama 30B Supercot?

Llama 30B Supercot requires approximately 11.5 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 Llama 30B Supercot and how large is it?

Llama 30B Supercot is developed by ausboss, 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 Llama 30B Supercot perform on standard benchmarks?

Llama 30B Supercot has the following published scores: MMLU 56.56. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 30B Supercot by ausboss — VRAM 11.5GB, 2K context

Name: Llama 30B Supercot
Author: ausboss

Llama 30B Supercot is an open-source language model by ausboss. Features: 30b LLM, VRAM: 11.5GB, Context: 2K, LLM Explorer Score: 0.09, Arc: 64.9, HellaSwag: 85.1, MMLU: 56.6, GSM8K: 11.9.

Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/ausboss/llama-30b-supercot

Llama 30B Supercot Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Applications:

language generation, contextual text generation

Primary Use Cases:

structured text generation based on instructions

Additional Notes

Merge the LLaMa model with SuperCOT-LoRA for enhanced contextual response generation.

Input Output

Input Format:

Structured prompting format with instruction, input, and response sections.

Accepted Modalities:

text

Output Format:

Textual response based on provided instruction and context.

Performance Tips:

Use specific prompt suffixes to improve output quality.

LLM Name	Llama 30B Supercot
Repository 🤗	https://huggingface.co/ausboss/llama-30b-supercot
Model Size	30b
Required VRAM	11.5 GB
Updated	2026-07-31
Maintainer	ausboss
Model Type	llama
Model Files	0.0 GB: 1-of-243 0.4 GB: 2-of-243 0.4 GB: 3-of-243 0.2 GB: 4-of-243 0.2 GB: 5-of-243 0.3 GB: 6-of-243 0.3 GB: 7-of-243 0.2 GB: 8-of-243 0.2 GB: 9-of-243 0.3 GB: 10-of-243 0.3 GB: 11-of-243 0.2 GB: 12-of-243 0.2 GB: 13-of-243 0.3 GB: 14-of-243 0.3 GB: 15-of-243 0.2 GB: 16-of-243 0.2 GB: 17-of-243 0.3 GB: 18-of-243 0.3 GB: 19-of-243 0.2 GB: 20-of-243 0.2 GB: 21-of-243 0.3 GB: 22-of-243 0.3 GB: 23-of-243 0.2 GB: 24-of-243 0.2 GB: 25-of-243 0.3 GB: 26-of-243 0.3 GB: 27-of-243 0.2 GB: 28-of-243 0.2 GB: 29-of-243 0.3 GB: 30-of-243 0.3 GB: 31-of-243 0.2 GB: 32-of-243 0.2 GB: 33-of-243 0.3 GB: 34-of-243 0.3 GB: 35-of-243 0.2 GB: 36-of-243 0.2 GB: 37-of-243 0.3 GB: 38-of-243 0.3 GB: 39-of-243 0.2 GB: 40-of-243 0.2 GB: 41-of-243 0.3 GB: 42-of-243 0.3 GB: 43-of-243 0.2 GB: 44-of-243 0.2 GB: 45-of-243 0.3 GB: 46-of-243
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.0
Vocabulary Size	32000
Torch Data Type	float16

Rank the Llama 30B Supercot 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 Llama 30B Supercot

Model	Likes	Downloads	VRAM
Llama 30B Supercot GGUF	0	269	13 GB
Llama 30B Supercot 4bit	1	7	16 GB

Best Alternatives to Llama 30B Supercot

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 ausboss/llama-30b-supercot.