Aria — Hardware Requirements & GPU Compatibility
Vision
Aria is Rhymes AI's multimodal mixture-of-experts model with 25.3 billion total and about 3.9 billion active parameters per token, per the card, built to handle text, images and video in one model. The card describes it as natively multimodal, with 3.9 billion activated parameters for the language side, and reports results against Pixtral 12B, Llama 3.2 11B, GPT-4o mini and Gemini 1.5 Flash, including strong document and video understanding. Because all experts must be loaded, it needs roughly a high-end single GPU or a large-memory machine even when quantized, though decoding is fast for its size. The context window is 65,536 tokens, which the card describes as multimodal input of up to 64K tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in September 2024, it was later followed by Aria-Base-8K and Aria-Base-64K base checkpoints for research and continued training.
43.6K downloads
639 likesSpecifications
- Publisher
- rhymes-ai
- Parameters
- 25.3B
- Architecture
- AriaForConditionalGeneration
- Context Length
- 65,536 tokens
- Vocabulary Size
- 100,352
- Release Date
- 2024-09-26
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Aria Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 11.6 GB | 29.9 GB | 10.76 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 13.2 GB | 31.4 GB | 12.34 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 16.1 GB | 34.3 GB | 15.18 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 18.9 GB | 37.1 GB | 18.03 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 21.8 GB | 40.0 GB | 20.88 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 26.2 GB | 44.4 GB | 25.31 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 51.5 GB | 69.7 GB | 50.61 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Aria?
Q4_K_M · 16.1 GBAria (Q4_K_M) requires 16.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. Using the full 66K context window can add up to 18.2 GB, bringing total usage to 34.3 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Aria?
Q4_K_M · 16.1 GB41 devices with unified memory can run Aria, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightFrequently Asked Questions
- How much VRAM does Aria need?
Aria requires 16.1 GB of VRAM at Q4_K_M, or 51.5 GB at BF16. Full 66K context adds up to 18.2 GB (34.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 25.3B × 4.8 bits ÷ 8 = 15.2 GB
KV Cache + Overhead ≈ 0.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 19.1 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M16.1 GBQ4_K_M + full context34.3 GB- Can NVIDIA GeForce RTX 4090 run Aria?
Yes, at Q6_K (21.8 GB) or lower. Higher quantizations like Q8_0 (26.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Aria?
For Aria, Q4_K_M (16.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (18.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 11.6 GB.
VRAM requirement by quantization
Q2_K11.6 GBQ4_K_M ★16.1 GBQ5_K_M18.9 GBQ6_K21.8 GBQ8_026.2 GBBF1651.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Aria on a Mac?
Aria requires at least 11.6 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Aria locally?
Yes — Aria can run locally on consumer hardware. At Q4_K_M quantization it needs 16.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Aria?
At Q4_K_M, Aria can reach ~161 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~168 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 ÷ 16.1 × 0.65 = ~477 tok/s
Estimated speed at Q4_K_M (16.1 GB)
~477 tok/s~168 tok/s~477 tok/s~409 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Aria?
At Q4_K_M, the download is about 15.18 GB. The full-precision BF16 version is 50.61 GB. The smallest option (Q2_K) is 10.76 GB.
- Which GPUs can run Aria?
8 consumer GPUs can run Aria at Q4_K_M (16.1 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Aria?
41 devices with unified memory can run Aria at Q4_K_M (16.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.