What are the hardware requirements for Kudzu 8B?

Kudzu 8B requires approximately 16.1 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 Kudzu 8B and how large is it?

Kudzu 8B is developed by lodrick-the-lafted, 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 Kudzu 8B perform on standard benchmarks?

Kudzu 8B has the following published scores: MMLU 68.14. Compare against reference models on this page or on the LLM Explorer leaderboards.

Kudzu 8B by lodrick-the-lafted — VRAM 16.1GB, 8K context

Name: Kudzu 8B
Author: lodrick-the-lafted

Kudzu 8B is an open-source language model by lodrick-the-lafted. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: apache-2.0, Instruction-Based, Merged, LLM Explorer Score: 0.14, Arc: 62.5, HellaSwag: 80.3, MMLU: 68.1, GSM8K: 63.1.

Merged Model Base model:cgato/l3-thespice-8... Base model:edgerunners/meta-ll... Base model:lodrick-the-lafted/... Base model:lodrick-the-lafted/... Base model:lodrick-the-lafted/... Base model:unsloth/llama-3-8b-... Conversational Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/lodrick-the-lafted/Kudzu-8B

Kudzu 8B Parameters and Internals

Additional Notes

Fresh out of the mergekit-evolve kitchen, this is a merge model using wmdp as the scoring method for evolve. Has a mix of ablated models and does not exhibit the 'Ahaha!' interjections seen in Llama-3.

LLM Name	Kudzu 8B
Repository 🤗	https://huggingface.co/lodrick-the-lafted/Kudzu-8B
Base Model(s)	Olethros 8B Limon 8B Rummage 8B cgato/L3-TheSpice-8b-v0.8.3 Llama 3 8B Instruct ... Ortho Baukit 10fail 1000total lodrick-the-lafted/Olethros-8B lodrick-the-lafted/Limon-8B lodrick-the-lafted/Rummage-8B cgato/L3-TheSpice-8b-v0.8.3 unsloth/llama-3-8b-Instruct Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total
Merged Model	Yes
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-07-26
Maintainer	lodrick-the-lafted
Model Type	llama
Instruction-Based	Yes
Model Files	16.1 GB: 1-of-1
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Kudzu 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 Kudzu 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
Zero Llama 3.1 8B Beta6	1048K / 16.1 GB	7	1

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