NVIDIA GeForce RTX 3080 10GB
10 GB · 760 GB/s · 320 W
Prices
Every retailer we track in the UK, 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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | fits | 17.1 GB | 32k56k with q8 cache | 28tok/sest. | 468 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | fits | 17.4 GB | 27k48k with q8 cache | 27tok/sest. | 468 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | fits | 17.4 GB | 28k50k with q8 cache | 27tok/sest. | 468 tok/s | chat, coding |
| Gemma 4 26B-A4B | UD-Q4_K_M | fits | 17.3 GB | 67k111k with q8 cache | 94tok/sest. | 3058 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | fits | 18.6 GB | 11k19k with q8 cache | 81tok/sest. | 2246 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q5_K_M | fits | 18.0 GB | 12k23k with q8 cache | 26tok/sest. | 528 tok/s | chat |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 107tok/sest. | 2905 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 36tok/sest. | 1066 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 236k256k with q8 cache | 48tok/sest. | 1349 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q4_K_M | fits | 17.6 GB | 22k43k with q8 cache | 27tok/sest. | 475 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q5_K_M | fits | 18.0 GB | 12k23k with q8 cache | 26tok/sest. | 528 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 26k48k with q8 cache | 30tok/sest. | 876 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 18k34k with q8 cache | 28tok/sest. | 814 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 65k119k with q8 cache | 48tok/sest. | 1424 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 48tok/sest. | 1424 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 15k16k with q8 cache | 27tok/sest. | 819 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 98tok/sest. | 2717 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 67k121k with q8 cache | 46tok/sest. | 1331 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 55k101k with q8 cache | 44tok/sest. | 1321 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 56tok/sest. | 1635 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 193tok/sest. | 9544 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 88k128k with q8 cache | 61tok/sest. | 1471 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.4 GB | – | 15tok/sest. | 830 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 19.6 GB | –4k with q8 cache | 18tok/sest. | 398 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.8 GB | – | 22tok/sest. | 1104 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 22.0 GB | – | 62tok/sest. | 3646 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.8 GB | – | 6tok/sest. | 397 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 21.9 GB | – | 64tok/sest. | 3657 tok/s | chat, coding, agents, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 18tok/sest. | 3028 tok/s | chat |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 19.2 GB | 4k7k with q8 cache | 93tok/sest. | 2867 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 37tok/sest. | 2964 tok/s | chat, coding, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 21.6 GB | – | 11tok/sest. | 332 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 21.6 GB | – | 10tok/sest. | 346 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | offload | 43.2 GB | – | 2tok/sest. | 115 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.2 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.3 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.6 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 60.5 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.6 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 3080 10GB
- Memory
- 10 GB GDDR6X
- Memory bus
- 320-bit
- Memory bandwidth
- 760 GB/s
- FP16 compute
- 59.5 TFLOPS
- Software
- CUDA
- Board power
- 320 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16