What are the hardware requirements for Mergefodder1?

Mergefodder1 requires approximately 9.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mergefodder1 and how large is it?

Mergefodder1 is developed by jeiku, a model with 4.5b 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 Mergefodder1?

Mergefodder1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mergefodder1 by jeiku — VRAM 9.1GB, 128K context

Name: Mergefodder1
Author: jeiku

Mergefodder1 is an open-source language model by jeiku. Features: 4.5b LLM, VRAM: 9.1GB, Context: 128K, Merged, LLM Explorer Score: 0.14.

Merged Model Base model:jeiku/luxemaelstrom Base model:jeiku/neurodeed Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jeiku/mergefodder1

Mergefodder1 Parameters and Internals

Model Type

merge

Additional Notes

This model is the result of merging the pre-trained language models `jeiku/neurodeed` and `jeiku/luxemaelstrom` using the SLERP merge method provided by mergekit. The merge configuration involved setting the `t` parameter to 0.5 with the dtype `bfloat16`.

LLM Name	Mergefodder1
Repository 🤗	https://huggingface.co/jeiku/mergefodder1
Base Model(s)	Neurodeed Luxemaelstrom jeiku/neurodeed jeiku/luxemaelstrom
Merged Model	Yes
Model Size	4.5b
Required VRAM	9.1 GB
Updated	2026-06-28
Maintainer	jeiku
Model Type	llama
Model Files	5.0 GB: 1-of-2 4.1 GB: 2-of-2
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.44.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Mergefodder1 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 Mergefodder1

Best Alternatives	Context / RAM	Downloads	Likes
Hamanasu KTO V2	128K / 9 GB	184	0
Mergefodder2	128K / 9.1 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than jeiku/mergefodder1.