llmrun
MicrosoftAionInstructForCausalLM

Aion 1.0 Instruct 2.3B — Hardware Requirements & GPU Compatibility

ChatSummaryFunctions

Aion 1.0 Instruct 2.3B is a 2.3B-parameter open language model from Microsoft. It supports a context window of up to 32,768 tokens. At BF16 it needs about 5.03 GB of VRAM — see which GPUs and Macs can run it below.

2.3B params · dense33K contextMIT1.6K downloads175 likes
S

Runs great on a 24 GB GPU

Runs from8 GB BF16 · 32KBest on24 GB BF16 · ~130 tok/s · 32KMacs from16 GB BF16 · ~28 tok/s

MIT

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Aion 1.0 Instruct 2.3B

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

vLLM
one command · needs vLLM installed
$vllm serve microsoft/Aion-1.0-Instruct-2.3B --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 2080 Ti (11 GB) (4 GB headroom) · BF16

Generation speed
~80 tok/s
generation speed
Cost per 1M output tokens
$0.31
per 1M output tokens

How Much VRAM Does Aion 1.0 Instruct 2.3B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
5.0 GB7.4 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 32K context · ~130 tok/s
est.calculated, no published file yet

Selected BF16

Brain floating point 16

6.1GBat 16K context

Weights
4.6 GB
KV cache
1.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 17.9 GB free · ~130 tok/s

≥50 tok/s needs ≥387 GB/s · RTX 5090 ~232, M5 Ultra ~171

Which Hardware Can Run Aion 1.0 Instruct 2.3B?

BF16 · 5.0 GB

Aion 1.0 Instruct 2.3B (BF16) requires 5.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 33K context window can add up to 2.3 GB, bringing total usage to 7.4 GB. 107 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce GTX 1660 SUPER. 172 devices with unified memory can run Aion 1.0 Instruct 2.3B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at BF16
8 GB · RTX 4060BF16 · 6.1 GB · ~35 tok/s · 32K8 GB tier →
12 GB · RTX 3060 12GBBF16 · 6.1 GB · ~47 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBBF16 · 6.1 GB · ~58 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceBF16 · 6.1 GB · ~130 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4BF16 · 6.1 GB · ~17 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxBF16 · 6.1 GB · ~76 tok/s · 32KMacs →

Alternatives to Aion 1.0 Instruct 2.3B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
LFM3 Omni 2BLiquid AI—2.4 GB~385same size
Qwen3.5 2BAlibaba—1.9 GB~370same size
Qwen3 VL 2B InstructAlibaba—3.5 GB~362same size
Qwen2 VL 2B InstructAlibaba—2.1 GB~390same size
Kimi K3 DSparkRadixArk—2.2 GB~381same size
Gemma 4 31B IT Speculator.eagle3RedHatAI—5 GB~205same size
Fine-tunes & variants(1)

Specifications

Publisher
Microsoft
Parameters
2.3B
Architecture
AionInstructForCausalLM
Context Length
32,768 tokens
Vocabulary Size
200,029
Release Date
2026-11-18
License
MIT

Frequently Asked Questions

How much VRAM does Aion 1.0 Instruct 2.3B need?

Aion 1.0 Instruct 2.3B requires 5.0 GB of VRAM at BF16. Full 33K context adds up to 2.3 GB (7.4 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 2.3B × 16 bits ÷ 8 = 4.6 GB

KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 2.8 GB (at full 33K context)

VRAM usage by quantization

5.0 GB
7.4 GB

Learn more about VRAM estimation →

Can I run Aion 1.0 Instruct 2.3B on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run Aion 1.0 Instruct 2.3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 5.0 GB of usable unified memory (RAM minus macOS overhead).

Can I run Aion 1.0 Instruct 2.3B locally?

Yes — Aion 1.0 Instruct 2.3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Aion 1.0 Instruct 2.3B?

At BF16, Aion 1.0 Instruct 2.3B can reach ~954 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~130 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 5.03 × 0.65 = ~1034 tok/s

Estimated speed at BF16 (5.0 GB)

~1034 tok/s
~130 tok/s
~1034 tok/s
~954 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Aion 1.0 Instruct 2.3B?

At BF16, the download is about 4.58 GB.

Which GPUs can run Aion 1.0 Instruct 2.3B?

107 consumer GPUs can run Aion 1.0 Instruct 2.3B at BF16. Top options include AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB, AMD Radeon RX 6600, AMD Radeon RX 5600 XT. 95 GPUs have plenty of headroom for comfortable inference.

Which devices can run Aion 1.0 Instruct 2.3B?

172 devices with unified memory can run Aion 1.0 Instruct 2.3B at BF16 (5.0 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.