What are the hardware requirements for Llama With Eeve New 03 150M?

Llama With Eeve New 03 150M requires approximately 0.6 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama With Eeve New 03 150M and how large is it?

Llama With Eeve New 03 150M is developed by kikikara, a model with 150m 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 Llama With Eeve New 03 150M?

Llama With Eeve New 03 150M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama With Eeve New 03 150M by kikikara — VRAM 0.6GB, 32K context

Name: Llama With Eeve New 03 150M
Author: kikikara

Llama With Eeve New 03 150M is an open-source language model by kikikara. Features: 150m LLM, VRAM: 0.6GB, Context: 32K, LLM Explorer Score: 0.13.

Conversational Dataset:haerae-hub/k2-feedback Dataset:haerae-hub/korean-huma... Dataset:heegyu/aulm-0809 Dataset:heegyu/cot-collection-... Dataset:heegyu/kowikitext Dataset:heegyu/open-korean-ins... Dataset:instructkr/ko elo aren... Dataset:markrai/kocommercial-d... Dataset:maywell/ko wikidata qa Dataset:nlpai-lab/kullm-v2 Endpoints compatible Ko Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/kikikara/llama_with_eeve_new_03_150m

Llama With Eeve New 03 150M Parameters and Internals

Model Type

text generation

Additional Notes

Model adheres to guidelines specified in the System prompt, avoiding immoral, sexual, illegal, or socially unacceptable statements.

Supported Languages

ko (Proficient)

Training Details

Data Sources:

maywell/ko_wikidata_QA, nlpai-lab/kullm-v2, heegyu/kowikitext, MarkrAI/KoCommercial-Dataset, heegyu/CoT-collection-ko, HAERAE-HUB/Korean-Human-Judgements, instructkr/ko_elo_arena_0207, HAERAE-HUB/K2-Feedback, heegyu/open-korean-instructions, heegyu/aulm-0809

Model Architecture:

llama

Input Output

Input Format:

Prompts should include a specific system and user structure.

Accepted Modalities:

text

Output Format:

Text

LLM Name	Llama With Eeve New 03 150m
Repository 🤗	https://huggingface.co/kikikara/llama_with_eeve_new_03_150m
Model Size	150m
Required VRAM	0.6 GB
Updated	2026-07-27
Maintainer	kikikara
Model Type	llama
Model Files	0.6 GB
Supported Languages	ko
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.1
Tokenizer Class	LlamaTokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	40960
Torch Data Type	float32

Rank the Llama With Eeve New 03 150M 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 With Eeve New 03 150M

Best Alternatives	Context / RAM	Downloads	Likes
...ma With Eeve The Third 06 150M	32K / 0.6 GB	8	0
Llama With Eeve New 150m	32K / 0.6 GB	6	0
... Eeve The Third 04 Law 01 150M	32K / 0.6 GB	5	0
...th Eeve The Third 04 Math 150M	32K / 0.6 GB	5	0
...ma With Eeve The Third 04 150M	32K / 0.6 GB	3	1
Portimbria 150M	4K / 0.7 GB	62	10
Llm Jp 3 150M Instruct3	4K / 0.3 GB	565	4
Llm Jp 3 150M Instruct2	4K / 0.3 GB	6	0
Bee 150M Pt Base	2K / 0.6 GB	102	0
Llama 150M Fresh	2K / 0.9 GB	939	1

Note: green Score (e.g. "73.2") means that the model is better than kikikara/llama_with_eeve_new_03_150m.