NVIDIA GeForce RTX 4080 Super
16 GB · 736 GB/s · 320 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 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 30.5 GB | 132k232k with q8 cache | 15tok/sest. | 575 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 28.2 GB | 166k256k with q8 cache | 16tok/sest. | 575 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q4_K_M | fits | 29.7 GB | 141k256k with q8 cache | 15tok/sest. | 546 tok/s | chat, coding, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q5_K_M | fits | 29.0 GB | 197k256k with q8 cache | 55tok/sest. | 2796 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q5_K_M | fits | 28.3 GB | 165k256k with q8 cache | 16tok/sest. | 575 tok/s | chat, coding, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.6 GB | 176k256k with q8 cache | 39tok/sest. | 3394 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q5_K_M | fits | 28.9 GB | 204k256k with q8 cache | 55tok/sest. | 2796 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 28.4 GB | 169k198k with q8 cache | 26tok/sest. | 1319 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.1 GB | 128k | 48tok/sest. | 2198 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 16.0 GB | 256k | 30tok/sest. | 1411 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.8 GB | 256k | 33tok/sest. | 1678 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q5_K_M | fits | 30.2 GB | 128k | 15tok/sest. | 704 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q4_K_M | fits | 29.5 GB | 135k247k with q8 cache | 15tok/sest. | 661 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 30.2 GB | 40k | 15tok/sest. | 562 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.0 GB | 128k | 16tok/sest. | 850 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 40k | 16tok/sest. | 850 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.1 GB | 256k | 52tok/sest. | 2613 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.3 GB | 153k256k with q8 cache | 17tok/sest. | 861 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.6 GB | 128k | 15tok/sest. | 773 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 13.0 GB | 128k | 38tok/sest. | 2352 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.2 GB | 125k | 37tok/sest. | 3144 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.0 GB | 128k | 19tok/sest. | 928 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 44.0 GB | – | 12tok/sest. | 831 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 50.1 GB | – | 12tok/sest. | 1723 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.9 GB | – | 10tok/sest. | 1054 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 42.1 GB | – | 16tok/sest. | 737 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 50.1 GB | – | 14tok/sest. | 1884 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 35.2 GB | 100k183k with q8 cache | 6tok/sest. | 474 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 35.2 GB | – | 33tok/sest. | 3461 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.9 GB | 122k167k with q8 cache | 92tok/sest. | 2095 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 31.1 GB | 124k223k with q8 cache | 17tok/sest. | 808 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 52.3 GB | 40k | 2tok/sest. | 172 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 35.2 GB | 100k128k with q8 cache | 6tok/sest. | 474 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 52.3 GB | 43k80k with q8 cache | 2tok/sest. | 230 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 35.1 GB | 16k | 7tok/sest. | 520 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.8 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.4 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 65.4 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 67.1 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.5 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