RTX 3080: 10 GB, what it runs and what it costs

Name: NVIDIA GeForce RTX 3080 10GB
Brand: NVIDIA

Specs checked Sep 20, 2026 · Aliteq Team · How we compute this

The short answer

The NVIDIA GeForce RTX 3080 10GB has 10 GB of VRAM and 760 GB/s of memory bandwidth (2020). At Q4_K_M quality or better with an 8K context it runs 10 of the open models we track; the largest that fits with room to spare is Gemma 4 12B. We don't see it for rent on the providers we track right now.

VRAM: 10 GB
Bandwidth: 760 GB/s
Board power: 320 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

Not for rent on the providers we track right now. See every card that is.

Which AI models run on the RTX 3080

Computed by our VRAM engine for an 8K context: the best quality each model fits at in 10 GB. Speeds are upper-bound estimates from memory bandwidth, not benchmarks.

Model	Best fit	VRAM used	~tok/s
Gemma 3 12B	Q5_K_M	9 GB93% · tight	—
Gemma 4 12B	Q5_K_M	9 GB88%	—
Qwen3.5 9B	Q6_K	8 GB84%	—
Qwen3 8B	Q6_K	8 GB82%	—
Gemma 4 E4B	Q8_0	9 GB88%	—
Qwen2.5 7B Instruct	Q8_0	9 GB88%	—
Mistral 7B Instruct v0.3	Q8_0	9 GB90%	—
Gemma 4 E2B	Q8_0	6 GB59%	—
Qwen3 4B Instruct 2507	F16	9 GB94% · tight	—
Llama 3.2 3B Instruct	F16	8 GB76%	—

Fits only below Q4 quality: gpt-oss 20B (MoE) (Q2_K), DeepSeek R1 Distill 14B (IQ4_XS), Qwen2.5-Coder 14B (IQ4_XS), Qwen3 14B (Q4_0), Phi-4 14B (IQ4_XS).

Too big for 10 GB (rent a bigger card instead): what it costs to run Mistral Small 24B, what it costs to run Gemma 4 26B-A4B (MoE), what it costs to run Qwen3.5 27B, what it costs to run Qwen3.6 27B.

Check a model and context of your own in the VRAM calculator.

AI video on the RTX 3080

Alibaba's Wan 2.2 is an open video model you can run yourself in ComfyUI. With 10 GB the RTX 3080 fits:

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 3080

someone doubled a five-year-old GPU's memory to 20GB for cheap AI — I wouldn't plug it in

Cards to compare it with

Every card by VRAM tier: all GPUs for gaming and local AI.

RTX 3080: common questions

How much VRAM does the RTX 3080 have?

10 GB, with 760 GB/s of memory bandwidth, per the maker's specification.

What is the biggest AI model the RTX 3080 can run?

Of the open models we track, Gemma 4 12B is the largest that fits at Q4_K_M or better with an 8K context and room to spare (about 9 GB of 10 GB). Gemma 3 12B also squeezes in, but with almost no memory left for longer context. Bigger models only fit at lower-quality quants or need more memory.

Can I rent an RTX 3080 in the cloud?

We don't see it on Vast.ai, Runpod or the other providers we track right now. The cloud GPU table lists every card that is for rent.

Is 10 GB enough?

1080p and light 1440p gaming; small local models (7–8B) at good quality.