What are the hardware requirements for Llama 3 Natsuki Ddlc 8B V1?

Llama 3 Natsuki Ddlc 8B V1 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 Llama 3 Natsuki Ddlc 8B V1 and how large is it?

Llama 3 Natsuki Ddlc 8B V1 is developed by 922-CA, 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 Llama 3 Natsuki Ddlc 8B V1 perform on standard benchmarks?

Llama 3 Natsuki Ddlc 8B V1 has the following published scores: MMLU 64.75. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 Natsuki Ddlc 8B V1 by 922-CA — VRAM 16.1GB, 8K context

Name: Llama 3 Natsuki Ddlc 8B V1
Author: 922-CA

Llama 3 Natsuki Ddlc 8B V1 is an open-source language model by 922-CA. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3, Quantized, LLM Explorer Score: 0.14, Arc: 60.3, HellaSwag: 81, MMLU: 64.8, GSM8K: 41.9.

4bit Base model:finetune:unsloth/ll... Base model:unsloth/llama-3-8b-... Dataset:922-ca/nacha v1 En Endpoints compatible Llama Model-index Pytorch Quantized Region:us Safetensors Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/922-CA/Llama-3-natsuki-ddlc-8b-v1

Llama 3 Natsuki Ddlc 8B V1 Parameters and Internals

Model Type

text-generation

Additional Notes

This model is fine-tuned for the Natsuki character from the DDLC game. It is designed to emulate her personality closely and may generate outputs that might not align with reality. Use at your own risk.

Training Details

Data Sources:

922-CA/NaChA_v1

Methodology:

LoRA (Low-Rank Adaptation)

Model Architecture:

LoRA architecture with rank: 32, lora alpha: 32, trained for 1 epoch, learning rate: 2e-4, batch size: 2, grad steps: 4.

LLM Name	Llama 3 Natsuki Ddlc 8B V1
Repository 🤗	https://huggingface.co/922-CA/Llama-3-natsuki-ddlc-8b-v1
Base Model(s)	Llama 3 8B Bnb 4bit unsloth/llama-3-8b-bnb-4bit
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-08-15
Maintainer	922-CA
Model Type	llama
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4 5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Supported Languages	en
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|reserved_special_token_250\|>
Vocabulary Size	128256
Torch Data Type	float16

Rank the Llama 3 Natsuki Ddlc 8B V1 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 3 Natsuki Ddlc 8B V1

Best Alternatives	Context / RAM	Downloads	Likes
...B Instruct Gradient 1048K 4bit	1024K / 4.5 GB	10	2
...B Instruct Gradient 1048K 8bit	1024K / 8.6 GB	11	1
...truct Gradient 1048K Bpw6 EXL2	1024K / 6.7 GB	2	2
...truct Gradient 1048K Bpw5 EXL2	1024K / 5.8 GB	5	0
Llama 3 8B Instruct 1048K 4bit	1024K / 4.5 GB	525	25
Llama 3 8B Instruct 1048K 8bit	1024K / 8.6 GB	213	17
... Gradient 1048K 8.0bpw H8 EXL2	1024K / 8.6 GB	2	3
...ct Gradient 1048K Bpw2.25 EXL2	1024K / 3.4 GB	5	1
Llama 3 8B Instruct 262K 2bit	256K / 2.5 GB	11	1
...B Instruct 262k V2 EXL2 5.0bpw	256K / 5.8 GB	5	1

Note: green Score (e.g. "73.2") means that the model is better than 922-CA/Llama-3-natsuki-ddlc-8b-v1.