llmrun
MicrosoftQwen3ForCausalLM

Aion 1.0 Instruct 2.3B ONNX WebGPU — Hardware Requirements & GPU Compatibility

ChatSummaryFunctions

Aion 1.0 Instruct 2.3B ONNX WebGPU is a 2.3B-parameter open language model from Microsoft. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 1.84 GB of VRAM — see which GPUs and Macs can run it below.

2.3B params · dense33K contextMIT81 downloads11 likes
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 32KBest on24 GB Q4_K_M · ~356 tok/s · 32KMacs from8 GB Q4_K_M · ~39 tok/s

MIT

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Aion 1.0 Instruct 2.3B ONNX WebGPU

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-ONNX-WebGPU --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 3060 12GB (9 GB headroom) · Q4_K_M

Generation speed
~127 tok/s
generation speed
Cost per 1M output tokens
$0.13
per 1M output tokens

How Much VRAM Does Aion 1.0 Instruct 2.3B ONNX WebGPU Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
1.4 GB3.8 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~458 tok/s
1.6 GB3.9 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~415 tok/s
1.8 GB4.2 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~356 tok/s
2.1 GB4.5 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~312 tok/s
2.4 GB4.7 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~279 tok/s
2.8 GB5.1 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~237 tok/s
5.1 GB7.4 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 32K context · ~130 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

2.9GBat 16K context

Weights
1.4 GB
KV cache
1.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 21.1 GB free · ~356 tok/s

≥50 tok/s needs ≥141 GB/s · RTX 5090 ~633, M5 Ultra ~467

Which Hardware Can Run Aion 1.0 Instruct 2.3B ONNX WebGPU?

Q4_K_M · 1.8 GB

Aion 1.0 Instruct 2.3B ONNX WebGPU (Q4_K_M) requires 1.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 33K context window can add up to 2.4 GB, bringing total usage to 4.2 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Aion 1.0 Instruct 2.3B ONNX WebGPU, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 2.9 GB · ~96 tok/s · 32K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 2.9 GB · ~127 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 2.9 GB · ~158 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 2.9 GB · ~356 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 2.9 GB · ~46 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 2.9 GB · ~208 tok/s · 32KMacs →

Alternatives to Aion 1.0 Instruct 2.3B ONNX WebGPU

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
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
EXAONE 3.5 2.4B InstructLGAI-EXAONE—3.4 GB~412same size

Specifications

Publisher
Microsoft
Parameters
2.3B
Architecture
Qwen3ForCausalLM
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 ONNX WebGPU need?

Aion 1.0 Instruct 2.3B ONNX WebGPU requires 1.8 GB of VRAM at Q4_K_M, or 5.1 GB at BF16. Full 33K context adds up to 2.4 GB (4.2 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 2.3B × 4.8 bits ÷ 8 = 1.4 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

1.8 GB
4.2 GB

Learn more about VRAM estimation →

What's the best quantization for Aion 1.0 Instruct 2.3B ONNX WebGPU?

For Aion 1.0 Instruct 2.3B ONNX WebGPU, Q4_K_M (1.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.4 GB.

VRAM requirement by quantization

Q2_K
1.4 GB
Q4_K_M ★
1.8 GB
Q5_K_M
2.1 GB
Q6_K
2.4 GB
Q8_0
2.8 GB
BF16
5.1 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

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

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Aion 1.0 Instruct 2.3B ONNX WebGPU. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.8 GB of usable unified memory (RAM minus macOS overhead).

Can I run Aion 1.0 Instruct 2.3B ONNX WebGPU locally?

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

How fast is Aion 1.0 Instruct 2.3B ONNX WebGPU?

At Q4_K_M, Aion 1.0 Instruct 2.3B ONNX WebGPU can reach ~2609 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~356 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 ÷ 1.84 × 0.65 = ~2826 tok/s

Estimated speed at Q4_K_M (1.8 GB)

~2826 tok/s
~356 tok/s
~2826 tok/s
~2609 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 ONNX WebGPU?

At Q4_K_M, the download is about 1.38 GB. The full-precision BF16 version is 4.60 GB. The smallest option (Q2_K) is 0.98 GB.

Which GPUs can run Aion 1.0 Instruct 2.3B ONNX WebGPU?

114 consumer GPUs can run Aion 1.0 Instruct 2.3B ONNX WebGPU at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.

Which devices can run Aion 1.0 Instruct 2.3B ONNX WebGPU?

185 devices with unified memory can run Aion 1.0 Instruct 2.3B ONNX WebGPU at Q4_K_M (1.8 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.