NVIDIA GeForce RTX 5070
12 GB · 672 GB/s · 250 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | fits | 20.9 GB | 91k159k with q8 cache | 20tok/sest. | 408 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | fits | 21.3 GB | 86k150k with q8 cache | 20tok/sest. | 408 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | fits | 21.2 GB | 87k152k with q8 cache | 20tok/sest. | 408 tok/s | chat, coding |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 22.6 GB | 71k116k with q8 cache | 52tok/sest. | 2513 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | fits | 21.8 GB | 80k139k with q8 cache | 38tok/sest. | 1217 tok/s | chat, coding, agents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 62tok/sest. | 1878 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 30tok/sest. | 966 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 36tok/sest. | 1182 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q4_K_M | fits | 22.3 GB | 70k128k with q8 cache | 19tok/sest. | 457 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q6_K | fits | 21.8 GB | 70k127k with q8 cache | 19tok/sest. | 565 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q6_K | fits | 22.8 GB | 40k | 18tok/sest. | 495 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 92k128k with q8 cache | 23tok/sest. | 781 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 23tok/sest. | 781 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | fits | 22.3 GB | 16k | 19tok/sest. | 497 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 62tok/sest. | 2049 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 95k173k with q8 cache | 23tok/sest. | 773 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 80k128k with q8 cache | 21tok/sest. | 714 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 41tok/sest. | 1548 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 58tok/sest. | 3305 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 118k128k with q8 cache | 27tok/sest. | 839 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.1 GB | – | 12tok/sest. | 607 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 13tok/sest. | 1324 tok/s | chat |
| Gemma 4 31B | Q4_K_M | offload | 24.3 GB | 45k89k with q8 cache | 12tok/sest. | 357 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.3 GB | – | 16tok/sest. | 608 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 23.4 GB | 40k63k with q8 cache | 65tok/sest. | 2414 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 23.3 GB | 44k70k with q8 cache | 67tok/sest. | 2421 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 15tok/sest. | 1511 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.8 GB | 51k93k with q8 cache | 11tok/sest. | 381 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.5 GB | – | 20tok/sest. | 2383 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.0 GB | – | 38tok/sest. | 1673 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.8 GB | 44k79k with q8 cache | 19tok/sest. | 834 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.9 GB | 12k23k with q8 cache | 3tok/sest. | 160 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.8 GB | 51k93k with q8 cache | 11tok/sest. | 381 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.0 GB | 12k23k with q8 cache | 3tok/sest. | 198 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 | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.0 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 62.8 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 55.2 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 5070
- Memory
- 12 GB GDDR7
- Memory bus
- 192-bit
- Memory bandwidth
- 672 GB/s
- FP16 compute
- 62 TFLOPS
- Software
- CUDA
- Board power
- 250 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16