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 two of them run
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-Q6_K | fits | 26.1 GB | 132k232k with q8 cache | 17tok/sest. | 684 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 26.6 GB | 125k219k with q8 cache | 17tok/sest. | 684 tok/s | chat |
| Gemma 4 31B | Q6_K | fits | 30.7 GB | 64k122k with q8 cache | 15tok/sest. | 624 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 30.1 GB | 92k144k with q8 cache | 71tok/sest. | 4117 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 26.5 GB | 126k221k with q8 cache | 17tok/sest. | 684 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.9 GB | 176k256k with q8 cache | 48tok/sest. | 4215 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.7 GB | 109k170k with q8 cache | 72tok/sest. | 4117 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 27.8 GB | 116k198k with q8 cache | 36tok/sest. | 2042 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 29.5 GB | 72k131k with q8 cache | 15tok/sest. | 673 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 30.0 GB | 122k167k with q8 cache | 114tok/sest. | 3307 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 68tok/sest. | 3151 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 27.7 GB | 95k170k with q8 cache | 32tok/sest. | 1473 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 32tok/sest. | 1620 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 39tok/sest. | 1983 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q6_K | fits | 27.5 GB | 102k128k with q8 cache | 16tok/sest. | 766 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 29.5 GB | 72k128k with q8 cache | 15tok/sest. | 673 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.8 GB | 100k183k with q8 cache | 18tok/sest. | 948 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.1 GB | 40k | 17tok/sest. | 830 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 128k | 25tok/sest. | 1311 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 25tok/sest. | 1311 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.5 GB | 16k | 16tok/sest. | 833 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 68tok/sest. | 3438 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 153k256k with q8 cache | 25tok/sest. | 1297 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 128k | 23tok/sest. | 1198 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 45tok/sest. | 2597 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 64tok/sest. | 5543 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 128k | 30tok/sest. | 1408 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.1 GB | – | 17tok/sest. | 1186 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 18tok/sest. | 2560 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.0 GB | – | 11tok/sest. | 1226 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.3 GB | – | 25tok/sest. | 1193 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.2 GB | – | 3tok/sest. | 315 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 21tok/sest. | 2920 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.5 GB | – | 39tok/sest. | 4734 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.9 GB | 40k | 6tok/sest. | 318 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.0 GB | 43k80k with q8 cache | 6tok/sest. | 393 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.5 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.5 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.1 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 62.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 61.1 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