10GB · AI Score 2.3/100 · first-party measured on 12 AI workloads
2.3 AI Score ✓ Measured
Every number on this page is first-party: NVIDIA GeForce RTX 3080 was run on our pinned 12-workload AI suite on 2026-07-11, with under 0.5% run-to-run variance. On Llama 3.1 8B (Q4_K_M) NVIDIA GeForce RTX 3080 delivers about 125.85 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 10GB. For image generation, SDXL runs at 2.38 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 9 of the 12 workloads won't fit on 10GB at the tested precision, Qwen2.5-Coder 14B, Qwen3 32B, Llama 3.3 70B, Z-Image Turbo and others. We publish those as hard gates rather than quietly dropping to a smaller quant.
The 3080 sat at exactly its 320W limit on Llama 8B, it uses everything it's given. The thing that surprised me is how little the 10GB buys you over the 8GB cards for AI: still 8 of 12 workloads gated. One run (Qwen2.5-Coder 14B) came back as a fail that shouldn't have been, so that one's flagged until I re-run it. Quick note on the setup: all my AI benchmarking was done on rented cloud GPUs, I used all three of Vast.ai, RunPod and Modal depending on which had the card, and they all have their pros and cons. Same pinned harness on every run, and everything here got double-checked before it went up.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 184.08 tok/s | 2.9 GB peak190 W63°C0.97 tok/WQ4_K_M | ✓ Measured |
| Llama 3.1 8B | 125.85 tok/s | 4.9 GB peak250 W66°C0.5 tok/WQ4_K_M | ✓ Measured |
| Qwen2.5-Coder 14B | ✕ Won't fit needs ~12 GB | VRAM-gated at this precision | ✓ Measured |
| Qwen3 32B | ✕ Won't fit needs ~23 GB | VRAM-gated at this precision | ✓ Measured |
| Llama 3.3 70B | ✕ Won't fit needs ~46 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 4.76 images/min | 9.1 GB peak268 W71°C12.6 s/img | ✓ Measured |
| Z-Image Turbo | ✕ Won't fit needs ~13 GB | VRAM-gated at this precision | ✓ Measured |
| FLUX.1 dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Qwen-Image-Edit | ✕ Won't fit needs ~42 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | ✓ Measured |
| Wan 2.2 5B (720p) | ✕ Won't fit needs ~18 GB | VRAM-gated at this precision | ✓ Measured |
| Architecture | Ampere (GA102) |
| CUDA cores | 8,704 |
| VRAM | 10GB GDDR6X |
| Memory bus | 320-bit |
| Memory bandwidth | 760 GB/s |
| Boost clock | 1,710 MHz |
| TDP | 320 W |
| Process | 8nm |
| Interface | PCIe 4.0 x16 |
| Release date | 2020-09-17 |
| Launch MSRP | $699 |
NVIDIA GeForce RTX 3080 scores 2.3/100, #78 of 102. It ran 3 of 12; 9 exceeded its 10GB. Every figure here is our own measurement.
100% = this card, AI & Machine Learning headline metric (AI Score). #39 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA TITAN Xp | 113% | 2.6 | |
| AMD Radeon RX 7700 XT | 109% | 2.5 | |
| NVIDIA TITAN X (Pascal) | 109% | 2.5 | |
| AMD Radeon RX 6700 | 100% | 2.3 | |
| NVIDIA GeForce RTX 3080 | 100% | 2.3 | |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | 96% | 2.2 | |
| NVIDIA GeForce RTX 3070 Ti | 96% | 2.2 | |
| NVIDIA GeForce RTX 2080 Super | 91% | 2.1 | |
| NVIDIA GeForce RTX 3070 Founders Edition | 91% | 2.1 |
Same card, other workloads: NVIDIA GeForce RTX 3080 Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 28,300 million |
| Die size | 628.4 mm² |
| Fabricated by | Samsung |
| Transistor density | 45 million per mm² |
Denser than 49% of the 76 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
Can't run: 60-second AI short film (needs Qwen3 32B), 60-second AI short film, narrated (needs Qwen3 32B), 10 short social clips (needs Qwen3 32B), 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs Qwen3 32B), 20 long-form articles (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B), Character sheet, 12 poses (needs FLUX.1 dev), 100-photo restoration batch (needs FLUX.1 Kontext dev), 24-frame storyboard (needs Qwen3 32B), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).
This card is $699 to buy. The cheapest listed rate on Vast.ai is $0.029/hour, but that is the floor: we budget $0.035/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 20,086 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $25 | 27.5 years |
| 8 hours a day, working on it | 2,920 | $102 | 6.9 years |
| 24/7, always-on agent | 8,760 | $305 | 2.3 years |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.