NVIDIA GeForce RTX 4090
24 GB · 1,008 GB/s · 450 W
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | fits | 20.5 GB | 105k184k with q8 cache | 30tok/sest. | 1085 tok/s | chat, coding, agents |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 23.4 GB | 64k112k with q8 cache | 26tok/sest. | 1085 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | fits | 23.0 GB | 79k124k with q8 cache | 115tok/sest. | 6531 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | fits | 20.8 GB | 101k178k with q8 cache | 30tok/sest. | 1085 tok/s | chat, coding, agents |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 22.2 GB | 110k178k with q8 cache | 78tok/sest. | 6687 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 22.9 GB | 84k131k with q8 cache | 116tok/sest. | 6531 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | fits | 21.4 GB | 98k169k with q8 cache | 57tok/sest. | 3240 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.9 GB | 128k | 93tok/sest. | 4999 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.2 GB | 256k | 44tok/sest. | 2571 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.0 GB | 256k | 53tok/sest. | 3146 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q4_K_M | fits | 21.9 GB | 81k128k with q8 cache | 28tok/sest. | 1215 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q6_K | fits | 21.4 GB | 76k139k with q8 cache | 29tok/sest. | 1504 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q6_K | fits | 22.4 GB | 40k | 27tok/sest. | 1317 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.2 GB | 99k128k with q8 cache | 34tok/sest. | 2079 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.2 GB | 40k | 34tok/sest. | 2079 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q5_K_M | fits | 23.3 GB | 16k | 26tok/sest. | 1322 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 256k | 94tok/sest. | 5454 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.0 GB | 103k187k with q8 cache | 34tok/sest. | 2057 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.8 GB | 86k128k with q8 cache | 31tok/sest. | 1901 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 128k | 62tok/sest. | 4121 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.5 GB | 125k | 88tok/sest. | 8795 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.2 GB | 126k128k with q8 cache | 41tok/sest. | 2234 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 41.7 GB | – | 13tok/sest. | 1648 tok/s | chat |
| Gemma 4 31B | Q4_K_M | offload | 23.9 GB | 57k110k with q8 cache | 21tok/sest. | 977 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.8 GB | – | 14tok/sest. | 3591 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.9 GB | – | 18tok/sest. | 1653 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | 57k105k with q8 cache | 17tok/sest. | 1040 tok/s | chat, coding, agents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.8 GB | – | 17tok/sest. | 4097 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.1 GB | – | 22tok/sest. | 6487 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.6 GB | – | 47tok/sest. | 4562 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.4 GB | 54k97k with q8 cache | 32tok/sest. | 2280 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.5 GB | 16k30k with q8 cache | 4tok/sest. | 437 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | 57k105k with q8 cache | 17tok/sest. | 1040 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.6 GB | 16k30k with q8 cache | 4tok/sest. | 540 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.6 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 62.4 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4090
- Memory
- 24 GB GDDR6X
- Memory bus
- 384-bit
- Memory bandwidth
- 1,008 GB/s
- FP16 compute
- 165 TFLOPS
- Software
- CUDA
- Board power
- 450 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16