What are the hardware requirements for Llama 30B Supercot 4bit?

Llama 30B Supercot 4bit requires approximately 16.9 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 4bit and how large is it?

Llama 30B Supercot 4bit 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 4bit perform on standard benchmarks?

Llama 30B Supercot 4bit has the following published scores: MMLU 56.56. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 30B Supercot 4bit by ausboss — VRAM 16.9GB, 2K context

Name: Llama 30B Supercot 4bit
Author: ausboss

Llama 30B Supercot 4bit is an open-source language model by ausboss. Features: 30b LLM, VRAM: 16.9GB, Context: 2K, Quantized, LLM Explorer Score: 0.09, Arc: 64.9, HellaSwag: 85.1, MMLU: 56.6, GSM8K: 11.9.

4bit Endpoints compatible Llama Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/ausboss/llama-30b-supercot-4bit

Llama 30B Supercot 4bit Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Additional Notes

Compatible with 7B, 13B, and 30B 4-bit quantized LLaMa models, including ggml quantized converted bins. The structure of prompts becomes more critical for lower parameter sizes.

Training Details

Methodology:

LoRA training for adaptation with langchain prompting

Input Output

Input Format:

Instruction-Input-Response format

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use suggestion suffixes to improve output quality.

LLM Name	Llama 30B Supercot 4bit
Repository 🤗	https://huggingface.co/ausboss/llama-30b-supercot-4bit
Base Model(s)	Llama 30B Supercot ausboss/llama-30b-supercot
Model Size	30b
Required VRAM	16.9 GB
Updated	2026-08-01
Maintainer	ausboss
Model Type	llama
Model Files	16.9 GB
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.0
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 Llama 30B Supercot 4bit 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 Llama 30B Supercot 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Tenebra 30B Alpha01 FP16	16K / 65 GB	1833	9
Tenebra 30B Alpha01 4BIT	16K / 19.4 GB	73	1
...nebra 30B Alpha01 EXL2 2 80bpw	16K / 11.9 GB	4	1
...nebra 30B Alpha01 EXL2 2 50bpw	16K / 10.7 GB	6	0
Tenebra 30B Alpha01 EXL2 3bpw	16K / 12.7 GB	6	0
Tenebra 30B Alpha01 3BIT	16K / 12.9 GB	5	0
Platypus 30B SuperHOT 8K Fp16	8K / 65.2 GB	176	2
... 30B Supercot SuperHOT 8K Fp16	8K / 65.2 GB	141	4
GPlatty 30B SuperHOT 8K Fp16	8K / 65.2 GB	128	1
Tulu 30B Fp16	2K / 65.2 GB	325	5

Note: green Score (e.g. "73.2") means that the model is better than ausboss/llama-30b-supercot-4bit.