What are the hardware requirements for CosmicBun 8B?

CosmicBun 8B requires approximately 16 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CosmicBun 8B and how large is it?

CosmicBun 8B is developed by aloobun, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CosmicBun 8B perform on standard benchmarks?

CosmicBun 8B has the following published scores: MMLU 65.53. Compare against reference models on this page or on the LLM Explorer leaderboards.

CosmicBun 8B by aloobun — VRAM 16GB, 8K context

Name: CosmicBun 8B
Author: aloobun

CosmicBun 8B is an open-source language model by aloobun. Features: 8b LLM, VRAM: 16GB, Context: 8K, License: mit, Merged, LLM Explorer Score: 0.13, Arc: 61.9, HellaSwag: 84.3, MMLU: 65.5, GSM8K: 68.2.

Merged Model Arxiv:2306.01708 Arxiv:2311.03099 Base model:dphn/dolphin-2.9-ll... Base model:locutusque/llama-3-... Base model:weyaxi/einstein-v6.... Biology Chemistry Conversational Dolphin Endpoints compatible Llama Llama3 Math Model-index Physics Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/aloobun/CosmicBun-8B

CosmicBun 8B Parameters and Internals

Model Type

text-generation

Training Details

Data Sources:

cognitivecomputations/dolphin-2.9-llama3-8b, Weyaxi/Einstein-v6.1-Llama3-8B, Locutusque/llama-3-neural-chat-v1-8b

Methodology:

Merge Method using DARE TIES

Model Architecture:

Merged using DARE TIES method

LLM Name	CosmicBun 8B
Repository 🤗	https://huggingface.co/aloobun/CosmicBun-8B
Base Model(s)	cognitivecomputations/dolphin-2.9-llama3-8b Weyaxi/Einstein-v6.1-Llama3-8B Llama 3 Neural Chat V1 8B cognitivecomputations/dolphin-2.9-llama3-8b Weyaxi/Einstein-v6.1-Llama3-8B Locutusque/llama-3-neural-chat-v1-8b
Merged Model	Yes
Model Size	8b
Required VRAM	16 GB
Updated	2026-07-20
Maintainer	aloobun
Model Type	llama
Model Files	9.9 GB: 1-of-2 6.1 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	mit
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the CosmicBun 8B 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 CosmicBun 8B

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than aloobun/CosmicBun-8B.