RTX 3090: 24 GB, what it runs and what it costs
Specs checked · Rental prices from 18m ago · Aliteq Team · How we compute this
The short answer
The NVIDIA GeForce RTX 3090 has 24 GB of VRAM and 936 GB/s of memory bandwidth (2020). At Q4_K_M quality or better with an 8K context it runs 31 of the open models we track; the largest that fits with room to spare is Qwen3.6 35B-A3B (MoE). The cheapest rental right now is $0.080/hr (Vast.ai, interruptible).
- VRAM
- 24 GB
- Bandwidth
- 936 GB/s
- Board power
- 350 W
- Launched
- 2020
Source: NVIDIA specification · bandwidth not yet confirmed by a second source, so we don't estimate speed from it
Buy it or rent it
The RTX 3090 is mostly bought used now. Read our used-card buying guide before you pay for one: what to check, what it should cost, and when renting is cheaper.
| Provider | Type | From, per hour | Rent |
|---|---|---|---|
| Vast.ai | Spot (can be interrupted) | $0.080/hr | Vast.ai |
| Vast.ai | On demand | $0.100/hr | Vast.ai |
| Lium | On demand | $0.200/hr | Lium |
| Lium | Spot (can be interrupted) | $0.200/hr | Lium |
| Runpod | On demand | $0.500/hr | Runpod |
Lowest price per provider in our hourly snapshot (18m ago). Rent buttons are referral links. Every card side by side: cloud GPU prices.
Which AI models run on the RTX 3090
Computed by our VRAM engine for an 8K context: the best quality each model fits at in 24 GB. Speeds are upper-bound estimates from memory bandwidth, not benchmarks.
| Model | Best fit | VRAM used | ~tok/s |
|---|---|---|---|
| Qwen3.6 35B-A3B (MoE) | Q4_K_M | 21 GB88% | — |
| Ornith-1.5 35B-A3B (MoE) | Q4_K_M | 21 GB88% | — |
| Qwen3.5 35B-A3B (MoE) | Q4_K_M | 21 GB88% | — |
| DeepSeek R1 Distill 32B | Q5_0 | 24 GB100% · tight | — |
| Qwen2.5 Coder 32B | Q5_0 | 24 GB100% · tight | — |
| Qwen2.5 32B Instruct | Q5_0 | 24 GB100% · tight | — |
| Qwen3 32B | Q5_0 | 24 GB100% · tight | — |
| NVIDIA Nemotron 3 Nano 30B-A3B (MoE) | Q5_K_M | 22 GB90% · tight | — |
| Gemma 4 31B | Q5_K_M | 22 GB92% · tight | — |
| Qwen3 30B-A3B (MoE) | Q5_K_M | 22 GB91% · tight | — |
| Qwen3-Coder 30B-A3B (MoE) | Q5_K_M | 22 GB91% · tight | — |
| Qwen3.5 27B | Q6_K | 22 GB94% · tight | — |
Fits only below Q4 quality: Mixtral 8x7B (MoE) (Q3_K_M).
Too big for 24 GB (rent a bigger card instead): what it costs to run DeepSeek R1 Distill 70B, what it costs to run Qwen3-Coder-Next 80B-A3B (MoE), what it costs to run Qwen3-Next 80B-A3B (MoE), what it costs to run GLM-4.5-Air (MoE).
Check a model and context of your own in the VRAM calculator.
AI video on the RTX 3090
Alibaba's Wan 2.2 is an open video model you can run yourself in ComfyUI. With 24 GB the RTX 3090 fits:
- Wan 2.2 14B at 640x640 with fp8 weights (24 GB and up, per Runpod's Wan 2.2 guide)
- Wan 2.2 5B, with ComfyUI's native offloading (8 GB and up, per ComfyUI's Wan 2.2 docs)
What each setup needs, the cheapest card to rent and what one clip costs: cloud GPUs for ComfyUI with Flux and Wan 2.2. Against an app or an API: AI video cost per clip, app vs API vs rented GPU. Rather not run a model yourself? Hosted video models such as Seedance, Veo and Hailuo are compared in Kling AI alternatives, priced per clip.
Our guides on the RTX 3090
- CompareNew RTX 5060 Ti 16GB or a used RTX 3090 for local AI?
- CompareRTX 4090 or RTX 3090 for local AI? Same 24GB, so buy the 3090 unless you paste long prompts all day
- CompareTwo RTX 3090s or one RTX 5090 for local LLMs? The answer isn't the one everyone gives
- CompareShould you rent a cloud GPU or buy one for AI? Rent, unless you'll pass about 2,000 hours
- CompareShould you buy a Mac Studio or an NVIDIA PC for local AI?
- Two used RTX 3090s or one RTX 5090 for local AI: which should you buy?
- Is a used RTX 3090 still worth it for local AI, and what should you pay?
- What's the cheapest cloud GPU for ComfyUI with Flux or Wan 2.2 video?
- What's the best GPU for local AI right now? The card with enough VRAM for your model, at the lowest price
- Is a used AMD Instinct MI50 32GB worth buying for local AI in 2026?
- What's the cheapest way to run a 70B model: used GPUs, a Mac or renting?
- Which GPU should you buy for Stable Diffusion and Flux? The pick for every budget
Cards to compare it with
- AMD Radeon RX 7900 XTX · 24 GB
- RTX 4090 · 24 GB
- RTX 3090 Ti · 24 GB
- RTX A5000 · 24 GB
- AMD Radeon RX 7900 XT · 20 GB
- RTX 5080 · 16 GB
Every card by VRAM tier: all GPUs for gaming and local AI.