What are the hardware requirements for MiniSeek V1 Base?

MiniSeek V1 Base requires approximately 0.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MiniSeek V1 Base and how large is it?

MiniSeek V1 Base is developed by wyf-yfw, a model with 186.9m 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 MiniSeek V1 Base?

MiniSeek V1 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniSeek V1 Base by wyf-yfw — VRAM 0.7GB

Name: MiniSeek V1 Base
Author: wyf-yfw

MiniSeek V1 Base is an open-source language model by wyf-yfw. Features: 186.9m LLM, VRAM: 0.7GB, License: mit.

Chinese Conversational Custom code Decoder-only En Miniseek Miniseek moe Miniseek v Moe Pretrained Pytorch Region:us Safetensors V41-flash Zh

Model Card on HF 🤗: https://huggingface.co/wyf-yfw/MiniSeek-V1-base

MiniSeek V1 Base Parameters and Internals

LLM Name	MiniSeek V1 Base
Repository 🤗	https://huggingface.co/wyf-yfw/MiniSeek-V1-base
Model Size	186.9m
Required VRAM	0.7 GB
Updated	2026-11-02
Maintainer	wyf-yfw
Model Type	miniseek_v
Model Files	0.7 GB
Supported Languages	zh en
Model Architecture	MiniSeekVForCausalLM
License	mit
Model Max Length	32768
Transformers Version	5.20.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	6400

Rank the MiniSeek V1 Base 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