What are the hardware requirements for MNN Pocket 0.3B RU Chat?

MNN Pocket 0.3B RU Chat requires approximately 0.6 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 RU Chat and how large is it?

MNN Pocket 0.3B RU Chat is developed by Rahspide, 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 RU Chat?

MNN Pocket 0.3B RU Chat 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 RU Chat by Rahspide — VRAM 0.6GB, 40K context

Name: MNN Pocket 0.3B RU Chat
Author: Rahspide

MNN Pocket 0.3B RU Chat is an open-source language model by Rahspide. Features: 0.3b LLM, VRAM: 0.6GB, Context: 40K, License: apache-2.0.

Assistant Base model:quantized:rahspide/... Base model:rahspide/mnn-pocket... Chat Conversational Dataset:huggingfaceh4/ultracha... Dataset:ilyagusev/saiga scored En Endpoints compatible Gguf Mnn On-device Qwen3 Region:us Ru Russian Safetensors Work-in-progress

Model Card on HF 🤗: https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat

MNN Pocket 0.3B RU Chat Parameters and Internals

LLM Name	MNN Pocket 0.3B RU Chat
Repository 🤗	https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat
Base Model(s)	Rahspide/MNN-Pocket-0.3B-RU Rahspide/MNN-Pocket-0.3B-RU
Model Size	0.3b
Required VRAM	0.6 GB
Updated	2026-11-12
Maintainer	Rahspide
Model Type	qwen3
Model Files	0.6 GB
Supported Languages	ru en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	5.20.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	65536
Errors	replace

Rank the MNN Pocket 0.3B RU Chat 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 RU Chat

Best Alternatives	Context / RAM	Downloads	Likes
MNN Pocket 0.3B RU	40K / 0.6 GB	624	1
MNN Pocket 0.3B	40K / 0.7 GB	411	17
LittleLamb	40K / 0.6 GB	1133	8
MNN Pocket 0.3B Base	40K / 0.7 GB	9	0
LittleLamb ToolCalling	40K / 0.6 GB	212	1
VieNeu TTS 0.3B	4K / 0.2 GB	8555	22

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