What are the hardware requirements for StdMoE 1b14b 1T Preanneal?

StdMoE 1b14b 1T Preanneal requires approximately 54.3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed StdMoE 1b14b 1T Preanneal and how large is it?

StdMoE 1b14b 1T Preanneal is developed by allenai, a model with 13.6b 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 StdMoE 1b14b 1T Preanneal?

StdMoE 1b14b 1T Preanneal is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

StdMoE 1b14b 1T Preanneal by allenai — VRAM 54.3GB, 4K context

Name: StdMoE 1b14b 1T Preanneal
Author: allenai

StdMoE 1b14b 1T Preanneal is an open-source language model by allenai. Features: 13.6b LLM, VRAM: 54.3GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.25.

Arxiv:2605.06663 Baseline Conversational Custom code Dataset:allenai/olmoe-mix-0924 Emo En Mixture-of-experts Moe Pre-annealing Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/allenai/StdMoE_1b14b_1T_Preanneal

StdMoE 1b14b 1T Preanneal Parameters and Internals

LLM Name	StdMoE 1b14b 1T Preanneal
Repository 🤗	https://huggingface.co/allenai/StdMoE_1b14b_1T_Preanneal
Model Size	13.6b
Required VRAM	54.3 GB
Updated	2026-08-06
Maintainer	allenai
Model Type	emo
Model Files	5.0 GB: 1-of-11 5.0 GB: 2-of-11 5.0 GB: 3-of-11 5.0 GB: 4-of-11 5.0 GB: 5-of-11 5.0 GB: 6-of-11 5.0 GB: 7-of-11 5.0 GB: 8-of-11 5.0 GB: 9-of-11 5.0 GB: 10-of-11 4.3 GB: 11-of-11
Supported Languages	en
Model Architecture	EmoForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.57.1
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352

Rank the StdMoE 1b14b 1T Preanneal 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 StdMoE 1b14b 1T Preanneal

Best Alternatives	Context / RAM	Downloads	Likes
Emo 1b14b 1T	4K / 54.3 GB	441	28
StdMoE 1b14b 1T EmoAnnealed	4K / 54.3 GB	79	3
EMO	4K / 54.3 GB	50	5
StdMoE 1b14b 1T	4K / 54.3 GB	69	3

Note: green Score (e.g. "73.2") means that the model is better than allenai/StdMoE_1b14b_1T_Preanneal.