What are the hardware requirements for Tsukasa Llama 3 8B Qlora Gptq?

Tsukasa Llama 3 8B Qlora Gptq requires approximately 5.8 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 Tsukasa Llama 3 8B Qlora Gptq and how large is it?

Tsukasa Llama 3 8B Qlora Gptq is developed by ludis, a model with 8b 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 Tsukasa Llama 3 8B Qlora Gptq?

Tsukasa Llama 3 8B Qlora Gptq is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tsukasa Llama 3 8B Qlora Gptq by ludis — VRAM 5.8GB, 32K context

Name: Tsukasa Llama 3 8B Qlora Gptq
Author: ludis

Tsukasa Llama 3 8B Qlora Gptq is an open-source language model by ludis. Features: 8b LLM, VRAM: 5.8GB, Context: 32K, Quantized, LLM Explorer Score: 0.12.

4-bit Conversational Dataset:lemonilia/limarp Dataset:pygmalionai/pippa Endpoints compatible Gptq Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ludis/tsukasa-llama-3-8b-qlora-gptq

Tsukasa Llama 3 8B Qlora Gptq Parameters and Internals

Training Details

Data Sources:

PygmalionAI/PIPPA, lemonilia/LimaRP

Methodology:

gptq 4 bits, 0.1 damp, 128 group size, true sequential training

Context Length:

32000

Hardware Used:

8xH100 GPUs

Input Output

Input Format:

use the llama 3 instruct format `<|eot_id|>` as stopping sequence/string/token

Performance Tips:

Start with every sampler off, temperature at 1, and min p set to 0.05. For generating, try different settings such as 'Main choice', 'Alternative 1', or 'Alternative 2'.

LLM Name	Tsukasa Llama 3 8B Qlora Gptq
Repository 🤗	https://huggingface.co/ludis/tsukasa-llama-3-8b-qlora-gptq
Model Size	8b
Required VRAM	5.8 GB
Updated	2026-08-07
Maintainer	ludis
Model Type	llama
Model Files	4.7 GB: 1-of-2 1.1 GB: 2-of-2
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float16

Rank the Tsukasa Llama 3 8B Qlora Gptq 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 Tsukasa Llama 3 8B Qlora Gptq

Best Alternatives	Context / RAM	Downloads	Likes
...a 3 8B Instruct 262K 4bit GPTQ	256K / 5.8 GB	5	1
... 8B Instruct 262K 4bit GPTQ 02	256K / 5.7 GB	6	0
...Instruct V0.5 GPTQ Safetensors	128K / 4.9 GB	113	0
...lama 3.1 8B Instruct GPTQ INT4	128K / 5.8 GB	9169	42
...Instruct 80K Qlora Merged GPTQ	80K / 5.8 GB	6	0
Llama3 German 8B 32K GPTQ	64K / 5.7 GB	7	0
...oLeo Instruct 8B 32K V0.1 GPTQ	64K / 5.7 GB	5	0
Llama 3 Soliloquy 8B V2 GPTQ	24K / 5.7 GB	10	1
Llama 3 Soliloquy 8B GPTQ	16K / 5.7 GB	10	5
Meta Llama 3 8B Instruct GPTQ	8K / 5.8 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than ludis/tsukasa-llama-3-8b-qlora-gptq.