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…
Qué dice el vídeo
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.
¿Qué necesitas para ejecutarlo en casa? A 4 bits ocupa unos 4 gigabytes de memoria. El equipo doméstico más pequeño que lo aloja por completo es un RTX 4060. Con un RTX 3060 12 GB y 32 gigabytes de RAM escribe unos 135 tokens por segundo. Con un RTX 4090 y 64 gigabytes de RAM escribe unos 303 tokens por segundo.
Todavía no hay una API gratuita. Los pesos son abiertos: puedes descargarlos de Hugging Face con licencia MIT. Arena aún no lo ha clasificado: añadiremos la puntuación en cuanto lleguen los votos.
Compare Aion 1.0 Instruct 2.3B with every free model, and check what your own GPU can run, on FreeLLMArena.
Los datos
- Tamaño: 2.3B parámetros · contexto 32K · memoria a 4 bits unos 4 GB.
- RTX 3060 12 GB + 32 GB de RAM: unos 135 tokens/s
- RTX 4090 + 64 GB de RAM: unos 303 tokens/s
- RTX 5090 + 64 GB de RAM: unos 436 tokens/s
- Mac M4 Max 128 GB: unos 129 tokens/s
- NVIDIA DGX Spark 128 GB: unos 106 tokens/s
- Ryzen AI Max+ 395 128 GB: unos 100 tokens/s
- Mac Studio M3 Ultra 512 GB: unos 158 tokens/s
- Ficha del modelo: https://huggingface.co/microsoft/Aion-1.0-Instruct-2.3B
- Todos los modelos gratis, comparados: https://freellmarena.com
Hardware
Memoria a 4 bits con un contexto de 8K, de nuestro simulador. Para comprobar tu propio equipo, usa el simulador Ejecútalo en casa.
- Aion-1.0-Instruct-2.3B: unos 4 GB a 4 bits · el equipo doméstico más pequeño que lo aloja: RTX 4060 (8 GB) · Amazon ↗
- RTX 3060 12 GB + 32 GB de RAM: Aion-1.0-Instruct-2.3B, unos 135 tokens/s (todo en la GPU) · Amazon ↗
- RTX 4090 (24 GB) + 64 GB de RAM: Aion-1.0-Instruct-2.3B, unos 303 tokens/s (todo en la GPU) · Amazon ↗
- RTX 5090 (32 GB) + 64 GB de RAM: Aion-1.0-Instruct-2.3B, unos 436 tokens/s (todo en la GPU) · Amazon ↗
- Mac M4 Max 128 GB: Aion-1.0-Instruct-2.3B, unos 129 tokens/s (todo en la GPU) · Amazon ↗
- NVIDIA DGX Spark 128 GB: Aion-1.0-Instruct-2.3B, unos 106 tokens/s (todo en la GPU) · Amazon ↗
- Ryzen AI Max+ 395 128 GB: Aion-1.0-Instruct-2.3B, unos 100 tokens/s (todo en la GPU) · Amazon ↗
- Mac Studio M3 Ultra 512 GB: Aion-1.0-Instruct-2.3B, unos 158 tokens/s (todo en la GPU) · Amazon ↗
Como afiliados de Amazon, FreeLLMArena gana con las compras que cumplen los requisitos; los enlaces no cambian las cifras.
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 los modelos de IA gratis, clasificados
Tamaños, memoria, velocidad en tu tarjeta gráfica y dónde usar cada modelo gratis. Se actualiza cada noche.