Aion 1.0 Instruct 2.3B ONNX WebGPU — Hardware Requirements & GPU Compatibility
ChatSummaryFunctionsAion 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.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~356 tok/s · 32K)Macs from 8 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 serve microsoft/Aion-1.0-Instruct-2.3B-ONNX-WebGPU --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun 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.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | 3.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~458 tok/s | |
| 1.6 GB | 3.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~415 tok/s | |
| 1.8 GB | 4.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~356 tok/s | |
| 2.1 GB | 4.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~312 tok/s | |
| 2.4 GB | 4.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~279 tok/s | |
| 2.8 GB | 5.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~237 tok/s | |
| 5.1 GB | 7.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~130 tok/s |
Selected Q4_K_M
4-bit medium quantization2.9GBat 16K context
- Weights
- 1.4 GB
- KV cache
- 1.3 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Aion 1.0 Instruct 2.3B ONNX WebGPU?
Q4_K_M · 1.8 GBAion 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).
≤ 11 GB
≤ 11 GB tier →fits · 1.1 GB free · up to 16K ctx
68 GPUs · 1 Mac class · 3 device families
RTX 3080~269Simulate output on RTX 3080RTX 2080 Ti~218Simulate output on RTX 2080 TiRTX 3070 Ti~215Simulate output on RTX 3070 TiM3*8 GB~39Simulate output on iMac 24" M3 (8 GB)Orin Nano~36Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~26Simulate output on iPhone 1720 GB
fits · 17.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~261Simulate output on RX 7900 XT32–40 GB
fits · 29.1 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~633Simulate output on RTX 5090M5 Max*36 GB~175Simulate output on Mac Studio M5 Max (36 GB)M632 GB~65Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~106Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~72Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM3 Omni 2BLiquid AI | — | 2.4 GB | ~385 | same size |
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| Qwen2 VL 2B InstructAlibaba | — | 2.1 GB | ~390 | same size |
| Kimi K3 DSparkRadixArk | — | 2.2 GB | ~381 | same size |
| Gemma 4 31B IT Speculator.eagle3RedHatAI | — | 5 GB | ~205 | same size |
| EXAONE 3.5 2.4B InstructLGAI-EXAONE | — | 3.4 GB | ~412 | same 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
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
★ Recommended — best balance of quality and VRAM usage.
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)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
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.