What are the hardware requirements for MNN Pocket 0.3B Base?

MNN Pocket 0.3B Base requires approximately 0.7 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MNN Pocket 0.3B Base and how large is it?

MNN Pocket 0.3B Base is developed by taobao-mnn, a model with 0.3b 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 MNN Pocket 0.3B Base?

MNN Pocket 0.3B Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MNN Pocket 0.3B Base by taobao-mnn — VRAM 0.7GB, 40K context

Name: MNN Pocket 0.3B Base
Author: taobao-mnn

MNN Pocket 0.3B Base is an open-source language model by taobao-mnn. Features: 0.3b LLM, VRAM: 0.7GB, Context: 40K, License: apache-2.0.

Base Conversational En Mnn Mnn-pocket On-device Qwen3 Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B-Base

MNN Pocket 0.3B Base Parameters and Internals

LLM Name	MNN Pocket 0.3B Base
Repository 🤗	https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B-Base
Model Size	0.3b
Required VRAM	0.7 GB
Updated	2026-11-05
Maintainer	taobao-mnn
Model Type	qwen3
Model Files	0.7 GB
Supported Languages	en zh
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	65536
Errors	replace

Rank the MNN Pocket 0.3B 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

Best Alternatives to MNN Pocket 0.3B Base

Best Alternatives	Context / RAM	Downloads	Likes
LittleLamb	40K / 0.6 GB	1133	8
LittleLamb ToolCalling	40K / 0.6 GB	212	1
MNN Pocket 0.3B	40K / 0.7 GB	411	17
VieNeu TTS 0.3B	4K / 0.2 GB	8555	22

Note: green Score (e.g. "73.2") means that the model is better than taobao-mnn/MNN-Pocket-0.3B-Base.