llmrun
rhymes-aiAriaForConditionalGeneration

Aria — Hardware Requirements & GPU Compatibility

Vision

Aria is Rhymes AI's multimodal mixture-of-experts model featuring 25.3 billion total parameters, with around 3.9 billion active per token according to the card, designed to process text, images, and video all in one go. The documentation calls it natively multimodal, noting that the language component activates 3.9 billion parameters, while benchmarks compare performance against Pixtral 12B, Llama 3.2 11B, GPT-4o mini and Gemini 1.5 Flash, highlighting strong capabilities in document and video analysis. Since every expert must load into memory, it requires roughly a high-end single GPU or a large-memory machine even when quantized, although decoding remains fast for its scale. The model supports a context window of 65,536 tokens, which the card specifies as multimodal input up to 64K tokens. Released under the Apache 2.0 license, it allows unrestricted commercial and research use. Coming out in September 2024, subsequent releases included Aria-Base-8K and Aria-Base-64K base checkpoints for further training and research work.

25.3B params · MoE4.6B active66K contextApache 2.017.7K downloads638 likes
S

Runs great on a 24 GB GPU

Runs from16 GB Q2_K · 16KBest on24 GB Q4_K_M · ~168 tok/s · 16KMacs from24 GB Q4_K_M · ~53 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Aria

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 rhymes-ai/Aria --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 A6000 (48 GB) (27 GB headroom) · Q4_K_M

Generation speed
~136 tok/s
generation speed
Cost per 1M output tokens
$0.67
per 1M output tokens

How Much VRAM Does Aria Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
11.6 GB20.5 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~211 tok/s
13.2 GB22 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~193 tok/s
16.1 GB24.9 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 16K context · ~168 tok/s
18.9 GB27.7 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 16K context · ~149 tok/s
21.8 GB30.6 GB6-bit, very good — 6-bit quantization, very good qualityFits: 8K context · ~133 tok/s
26.2 GB35 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 30.3 GB
51.5 GB60.3 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingDoes not fit: needs 55.6 GB
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

20.2GBat 16K context

Weights
15.2 GB
KV cache
4.7 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 3.8 GB free · ~168 tok/s

≥50 tok/s needs ≥241 GB/s · RTX 5090 ~249, RTX 3090 Ti ~168

Which Hardware Can Run Aria?

Q4_K_M · 16.1 GB

Aria (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. 137 devices with unified memory can run Aria, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), NVIDIA RTX Spark N1X Laptop (32 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8–12 GB · RTX 4060, RTX 3060 12GBDoesn't fit — smallest quant needs 15.8 GB8 GB tier →12 GB tier →
16 GB · RTX 5060 Ti 16GBQ2_K · 15.8 GB · ~115 tok/s · 16K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 20.2 GB · ~168 tok/s · 16K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 20.2 GB · ~25 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 20.2 GB · ~76 tok/s · 64KMacs →

Alternatives to Aria

Similar models

4
ModelScoreVRAMtok/sWhy it is similar
Magistral Small 2509Mistral AI85.618.1 GB~43same size
Gemma 2 27B ITGoogle72.719.5 GB~37same size
LFM2.5 24B A2BLiquid AI—15 GB~221same size
Gemma 4 26B A4BGoogle—16.5 GB~171same size

Specifications

Publisher
rhymes-ai
Parameters
25.3B
Active parameters
4.6B per token
Architecture
AriaForConditionalGeneration
Context Length
65,536 tokens
Vocabulary Size
100,352
Release Date
2024-09-26
License
Apache 2.0

Frequently 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)

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 ≈ 19.1 GB (at full 66K context)

VRAM usage by quantization

16.1 GB
34.3 GB

Learn more about VRAM estimation →

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_K
11.6 GB
Q4_K_M ★
16.1 GB
Q5_K_M
18.9 GB
Q6_K
21.8 GB
Q8_0
26.2 GB
BF16
51.5 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Aria on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 115 other Macs can run Aria. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 16.1 GB of usable unified memory (RAM minus macOS overhead).

Can I run Aria locally?

Yes — Aria can run locally on consumer hardware. 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 = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 2.9 GB active ÷ (8000 × 0.65) = 0.556 ms, plus 28 layers × 0.055 ms = 1.540 ms, so 1000 ÷ 2.096 ms = ~477 tok/s

Estimated speed at Q4_K_M (16.1 GB)

~477 tok/s
~168 tok/s
~477 tok/s
~409 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 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. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.

Which devices can run Aria?

137 devices with unified memory can run Aria at Q4_K_M (16.1 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.