What are the hardware requirements for Small Fut Final?

Small Fut Final requires approximately 14.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Small Fut Final and how large is it?

Small Fut Final is developed by Dongwookss, a model with 7.2b 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 Small Fut Final?

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

Small Fut Final by Dongwookss — VRAM 14.4GB

Name: Small Fut Final
Author: Dongwookss

Small Fut Final is an open-source language model by Dongwookss. Features: 7.2b LLM, VRAM: 14.4GB, License: apache-2.0, LLM Explorer Score: 0.13.

Conversational Dataset:dongwookss/q a korean ... Endpoints compatible Ko Lora Mistral Region:us Safetensors Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Dongwookss/small_fut_final

Small Fut Final Parameters and Internals

Model Type

chatbot

Use Cases

Areas:

Research, Commercial applications

Applications:

Chatbots for futsal domain

Primary Use Cases:

Futsal assistant helper chatbot

Considerations:

Model answers are based on provided context; outside the context, it responds with uncertainty.

Additional Notes

The model uses speech in the '해요' style for responses, ending with a friendly '풋풋~!'

Supported Languages

ko (high)

Training Details

Data Sources:

q_a_korean_futsal

Methodology:

LLM 파인튜닝 (fine-tuning) with LoRA and SFT Trainer

Context Length:

4096

Hardware Used:

Colab environment with L4 GPU

Input Output

Input Format:

Chat input with instruction and response mechanism

Accepted Modalities:

Text

Output Format:

Text response

LLM Name	Small Fut Final
Repository 🤗	https://huggingface.co/Dongwookss/small_fut_final
Model Size	7.2b
Required VRAM	14.4 GB
Updated	2026-08-25
Maintainer	Dongwookss
Model Files	0.2 GB 4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Supported Languages	ko
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	32768
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|v_proj\|down_proj\|gate_proj\|q_proj\|k_proj\|up_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Small Fut Final 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 Small Fut Final

Best Alternatives	Context / RAM	Downloads	Likes
Zephyr Tuning V1	0K / 14.4 GB	1747	0
Spydaz Web AI 025	0K / 14.4 GB	44	0
Last Model Too Long Time	0K / 14.4 GB	8	1
Big Fut Final	0K / 14.4 GB	8	1
DummySFT	0K / 28.9 GB	8	0
Ethicalsft	0K / 28.9 GB	8	0
Tweet Sentiment Analyzer	0K / 7.7 GB	5	0
MistralRAG	0K / 14.4 GB	3	1
GAMA Code Generator V1.0	0K / 14.4 GB	7	0
G8 Mistral7b Qlora 1211 V09feb	0K / 14.4 GB	3	1

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