Hardware · NVIDIA
What AI models can the NVIDIA GeForce RTX 5090 run?
- VRAM
- 32.0 GB
- Usable for models
- 32.0 GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 104.8 TFLOPS
- Released
- 2025
- Launch price
- $1,999
Specifications
| Maker | NVIDIA |
|---|---|
| Type | Graphics card |
| Video memory (VRAM) | 32.0 GB |
| Usable for AI models | 32.0 GB |
| Memory bandwidth | 1,792 GB/s |
| FP16 compute | 104.8 TFLOPS |
| Interface | PCIe 5.0 |
| Released | 2025 |
| Launch price (US) | $1,999 |
9 products with the NVIDIA GeForce RTX 5090
- NVIDIA GeForce RTX 5090 Founders EditionMaker’s page (opens in a new tab)
- ROG Astral GeForce RTX 5090 32GB GDDR7 OC EditionMaker’s page (opens in a new tab)
- ASUS TUF Gaming GeForce RTX 5090 32GB GDDR7 OC EditionMaker’s page (opens in a new tab)
- AORUS GeForce RTX 5090 MASTER 32GMaker’s page (opens in a new tab)
- GeForce RTX 5090 GAMING OC 32GMaker’s page (opens in a new tab)
- MSI GeForce RTX 5090 32G SUPRIM LIQUID SOCMaker’s page (opens in a new tab)
- MSI GeForce RTX 5090 32G GAMING TRIO OCMaker’s page (opens in a new tab)
- ZOTAC GAMING GeForce RTX 5090 SOLID OCMaker’s page (opens in a new tab)
- PNY GeForce RTX 5090 ARGB EPIC-X RGB Overclocked Triple FanMaker’s page (opens in a new tab)
Best LLMs for the NVIDIA GeForce RTX 5090
| Grade · points | Model | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 97 ptsExcellent (S) · 97 of 100 points: Model quality 42.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.8 27B | Q6_K | 25.5 GB | 54.9 tok/s | Runs well |
| 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.6 27B | Q6_K | 25.5 GB | 54.9 tok/s | Runs well |
| 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.5 27B | Q6_K | 25.5 GB | 54.9 tok/s | Runs well |
| 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Gemma 4 26B-A4B | Q6_K | 23.8 GB | 201 tok/s | Runs well |
| 95 ptsExcellent (S) · 95 of 100 points: Model quality 41.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.6 35B-A3B | Q6_K | 31.8 GB | 254 tok/s | Tight fit |
| 95 ptsExcellent (S) · 95 of 100 points: Model quality 41.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.5 35B-A3B | Q6_K | 31.8 GB | 254 tok/s | Tight fit |
| 95 ptsExcellent (S) · 95 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | TMax 27B | Q6_K | 25.2 GB | 55.8 tok/s | Runs well |
| 94 ptsExcellent (S) · 94 of 100 points: Model quality 39.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Gemma 4 31B | Q5_K_M | 26.0 GB | 58.1 tok/s | Runs well |
| 94 ptsExcellent (S) · 94 of 100 points: Model quality 39.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Fara 1.5 27B | Q6_K | 25.2 GB | 55.8 tok/s | Runs well |
| 94 ptsExcellent (S) · 94 of 100 points: Model quality 40.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Ornith 1.5 35B-A3B | Q6_K | 31.8 GB | 254 tok/s | Tight fit |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 39.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Apodex 1.1 Mini (35B-A3B) | Q6_K | 31.8 GB | 254 tok/s | Tight fit |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 39.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Ornith 1.0 35B-A3B | Q6_K | 31.8 GB | 254 tok/s | Tight fit |
Best Image models for the NVIDIA GeForce RTX 5090
| Grade · points | Model | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Z-Image Turbo | FP16 | 22.7 GB | 2.1 s | Runs well |
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 | FLUX.2 [klein] 9B | Q8 GGUF | 20.5 GB | 1.7 s | Runs well |
| 90 ptsExcellent (S) · 90 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.1/15 | FLUX.1 Krea [dev] | FP8 | 19.6 GB | 9.0 s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 12.6/15, Memory use 15.0/15 | Z-Image | FP16 | 22.7 GB | 14 s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.1/15 | FLUX.1 [dev] | FP8 | 19.6 GB | 9.0 s | Runs well |
| 88 ptsExcellent (S) · 88 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.0/15 | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 0.8 s | Runs well |
Best Video models for the NVIDIA GeForce RTX 5090
| Grade · points | Model | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 82 ptsGreat (A) · 82 of 100 points: Model quality 30.0/45, Memory fit 23.0/25, Speed 15.0/15, Memory use 15.0/15 | LTX-Video 13B 0.9.8 (distilled) | FP8 | 30.1 GB | 45 s | Tight fit |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 32.6/45, Memory fit 23.0/25, Speed 11.6/15, Memory use 15.0/15 | FramePack I2V (HunyuanVideo 13B) | FP8 | 28.2 GB | 5.0 min | Tight fit |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 9.8/15, Memory use 15.0/15 | LTX-2.3 | Q4 GGUF | 24.5 GB | 7.0 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 15.0/15 | Wan 2.1 I2V 14B 480P | FP8 | 26.2 GB | 11.3 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 15.0/15 | Cosmos-Predict2 2B Video2World | FP8 | 26.8 GB | 3.1 min | Runs well |
Best LLMs by task on this hardware Open in Model Finder
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.