What are the hardware requirements for Ohara MoE 0.9B A91M Chat D12?

Ohara MoE 0.9B A91M Chat D12 requires approximately 3.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ohara MoE 0.9B A91M Chat D12 and how large is it?

Ohara MoE 0.9B A91M Chat D12 is developed by joey00072, a model with 911.3m 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 Ohara MoE 0.9B A91M Chat D12?

Ohara MoE 0.9B A91M Chat D12 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ohara MoE 0.9B A91M Chat D12 by joey00072 — VRAM 3.6GB

Name: Ohara MoE 0.9B A91M Chat D12
Author: joey00072

Ohara MoE 0.9B A91M Chat D12 is an open-source language model by joey00072. Features: 911.3m LLM, VRAM: 3.6GB, License: mit, MoE, LLM Explorer Score: 0.28.

Chat En Llama Mixture-of-experts Moe Nanochat Ohara Region:us Safetensors Shared-expert

Model Card on HF 🤗: https://huggingface.co/joey00072/ohara-moe-0.9B-a91M-chat-d12

Ohara MoE 0.9B A91M Chat D12 Parameters and Internals

LLM Name	Ohara MoE 0.9B A91M Chat D12
Repository 🤗	https://huggingface.co/joey00072/ohara-moe-0.9B-a91M-chat-d12
Model Size	911.3m
Required VRAM	3.6 GB
Updated	2026-08-19
Maintainer	joey00072
Model Files	3.6 GB
Supported Languages	en
License	mit
Model Max Length	2048
Is Biased	0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	50304
Errors	replace

Rank the Ohara MoE 0.9B A91M Chat D12 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