NVIDIA GeForce RTX 4080 Super
16 GB · 736 GB/s · 320 W
Prices
Every retailer we track in Germany, 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q6_K | fits | 12.9 GB | 245k256k with q8 cache | 37tok/sest. | 1411 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.4 GB | 155k256k with q8 cache | 33tok/sest. | 1678 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.7 GB | 256k | 52tok/sest. | 2613 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 12.6 GB | 128k | 38tok/sest. | 2352 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | UD-Q6_K | fits | 14.1 GB | 125k | 38tok/sest. | 3144 tok/s | chat, coding, long documents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 24.9 GB | – | 5tok/sest. | 435 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 25.3 GB | – | 4tok/sest. | 433 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 29.3 GB | – | 3tok/sest. | 383 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 24.6 GB | – | 15tok/sest. | 2128 tok/s | chat, coding, agents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 25.2 GB | – | 4tok/sest. | 433 tok/s | chat |
| Gemma 4 26B-A4B | UD-Q4_K_M | offload | 19.9 GB | – | 18tok/sest. | 2895 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 24.5 GB | – | 15tok/sest. | 2133 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 25.1 GB | – | 7tok/sest. | 994 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | 8k15k with q8 cache | 2tok/sest. | 335 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.8 GB | – | 12tok/sest. | 2447 tok/s | chat |
| gpt-oss 20B OpenAI | MXFP4 | offload | 15.7 GB | 116k128k with q8 cache | 41tok/sest. | 2167 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.5 GB | – | 19tok/sest. | 1444 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 30.7 GB | – | 4tok/sest. | 558 tok/s | chat |
| Gemma 3 27B | Q4_K_M | offload | 27.3 GB | – | 4tok/sest. | 510 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | 8k15k with q8 cache | 2tok/sest. | 335 tok/s | chat |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 29.1 GB | 43k79k with q8 cache | 3tok/sest. | 464 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 29.8 GB | 38k40k with q8 cache | 3tok/sest. | 391 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 24.1 GB | 68k124k with q8 cache | 5tok/sest. | 654 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 24.1 GB | 40k | 5tok/sest. | 654 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 34.7 GB | 16k | 2tok/sest. | 367 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 23.3 GB | 71k129k with q8 cache | 5tok/sest. | 675 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 26.6 GB | 58k107k with q8 cache | 4tok/sest. | 567 tok/s | chat, coding, agents |
| Llama 3.1 8B Meta | Q4_K_M | offload | 22.0 GB | 77k128k with q8 cache | 6tok/sest. | 749 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.4 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.0 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 43.6 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.5 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 49.7 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 65.0 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 41.7 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 66.7 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 49.7 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 51.9 GB | – | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 51.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.1 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4080 Super
- Memory
- 16 GB GDDR6X
- Memory bus
- 256-bit
- Memory bandwidth
- 736 GB/s
- FP16 compute
- 104 TFLOPS
- Software
- CUDA
- Board power
- 320 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16