Aion-1.0-Instruct-2.3B: How to Run It Free
Aion-1.0-Instruct-2.3B is a free, on-device 2.3 B parameter model with a 32 K token context. Learn its capabilities, benchmarks, and who can benefit from…
O que o vídeo diz
Microsoft released a 2.3 billion-parameter model that runs on-device. It can handle a 32 K token context, enough for multi-page documents.
Aion-1.0-Instruct-2.3B is Microsoft’s small language model for the Windows ecosystem. The model runs in PyTorch, ONNX and GGUF formats and is released under the MIT license on Hugging Face. It supports English, German, Spanish, Portuguese, Italian, French, Chinese and Japanese, and is built for on-device text generation tasks like summarization, rewriting and chat.
According to the model card, Aion is the foundational Small Language Model for Windows, optimized for responsive, private AI without constant cloud calls. Positional encoding combines RoPE with YaRN scaling, enabling the long 32 K context. Microsoft released the unquantized version first, promising later quantized releases.
The model card lists several benchmark scores. On the MMLU knowledge test the model scored 55.15 percent, while on the multilingual MMMLU it reached 45.51 percent. In math, GSM8K gave 74.91 percent and GSMPlus 49.56 percent. Instruction following measured by IFEval was 83.90 percent, and translation quality (chrF++) was 43.18 percent. These numbers reflect a small model’s performance compared with larger systems.
Because it is only 2.3 B parameters, Aion loads quickly and fits on modest hardware, a RTX 4060 can hold it fully in GPU memory. Token throughput ranges from 135 tokens per second on an RTX 3060 up to 436 tokens per second on an RTX 5090. The model excels at short-form generation and on-device privacy. However, the card warns that small models often miss fine details, struggle with multi-step reasoning and can generate inaccurate statements. Safety alignment is present but not as robust as larger models.
Aion-1.0-Instruct-2.3B is aimed at people who run AI at home and want a free, open model that works offline. Its long context makes it useful for document summarization, email thread analysis and other multi-page tasks. If you need a model that respects privacy and runs on a mid-range GPU, this is a solid choice. Keep in mind its reasoning limits and verify outputs for critical applications.
O que você precisa para rodá-lo em casa? Com 4 bits, ele ocupa cerca de 4 gigabytes de memória. A menor máquina doméstica que o comporta por inteiro é RTX 4060. Em RTX 3060 12 GB com 32 gigabytes de RAM, ele escreve cerca de 135 tokens por segundo. Em RTX 4090 com 64 gigabytes de RAM, ele escreve cerca de 303 tokens por segundo.
Ainda não há API grátis para ele. Os pesos são abertos: você pode baixá-los do Hugging Face sob a licença MIT. A Arena ainda não o classificou: adicionamos a pontuação assim que os votos chegarem.
Compare Aion 1.0 Instruct 2.3B with every free model, and check what your own GPU can run, on FreeLLMArena.
Os dados
- Tamanho: 2.3B de parâmetros · contexto de 32K · memória com 4 bits: cerca de 4 GB.
- RTX 3060 12 GB + 32 GB de RAM: cerca de 135 tokens/s
- RTX 4090 + 64 GB de RAM: cerca de 303 tokens/s
- RTX 5090 + 64 GB de RAM: cerca de 436 tokens/s
- Mac M4 Max 128 GB: cerca de 129 tokens/s
- NVIDIA DGX Spark 128 GB: cerca de 106 tokens/s
- Ryzen AI Max+ 395 128 GB: cerca de 100 tokens/s
- Mac Studio M3 Ultra 512 GB: cerca de 158 tokens/s
- Ficha do modelo: https://huggingface.co/microsoft/Aion-1.0-Instruct-2.3B
- Todos os modelos grátis, comparados: https://freellmarena.com
Hardware
Memória com 4 bits e contexto de 8K, segundo o nosso simulador. Para conferir a sua própria configuração, use o simulador Rode em casa.
- Aion-1.0-Instruct-2.3B: cerca de 4 GB com 4 bits · menor máquina doméstica que o comporta: RTX 4060 (8 GB) · Amazon ↗
- RTX 3060 12 GB + 32 GB de RAM: Aion-1.0-Instruct-2.3B, cerca de 135 tokens/s (totalmente na GPU) · Amazon ↗
- RTX 4090 (24 GB) + 64 GB de RAM: Aion-1.0-Instruct-2.3B, cerca de 303 tokens/s (totalmente na GPU) · Amazon ↗
- RTX 5090 (32 GB) + 64 GB de RAM: Aion-1.0-Instruct-2.3B, cerca de 436 tokens/s (totalmente na GPU) · Amazon ↗
- Mac M4 Max 128 GB: Aion-1.0-Instruct-2.3B, cerca de 129 tokens/s (totalmente na GPU) · Amazon ↗
- NVIDIA DGX Spark 128 GB: Aion-1.0-Instruct-2.3B, cerca de 106 tokens/s (totalmente na GPU) · Amazon ↗
- Ryzen AI Max+ 395 128 GB: Aion-1.0-Instruct-2.3B, cerca de 100 tokens/s (totalmente na GPU) · Amazon ↗
- Mac Studio M3 Ultra 512 GB: Aion-1.0-Instruct-2.3B, cerca de 158 tokens/s (totalmente na GPU) · Amazon ↗
Como Associada da Amazon, o FreeLLMArena ganha com compras qualificadas; os links não alteram os números.
Every number in this post comes from the FreeLLMArena data on 18 Nov 2026: Arena votes, Hugging Face sizes and our speed simulator. Download the video and its subtitles.
Todos os modelos de IA grátis, classificados
Tamanhos, memória, velocidade na sua GPU e onde usar cada modelo de graça. Atualizado toda noite.