NVIDIA GeForce RTX 4070 Super
12 GB · 504 GB/s · 220 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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 22.3 GB | 15k27k with q8 cache | 14tok/sest. | 559 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 22.8 GB | 8k14k with q8 cache | 14tok/sest. | 559 tok/s | – |
| Gemma 4 31B | Q5_K_M | fits | 22.7 GB | 8k23k with q8 cache | 14tok/sest. | 487 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | fits | 22.0 GB | 40k63k with q8 cache | 90tok/sest. | 4789 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 22.7 GB | 9k16k with q8 cache | 14tok/sest. | 559 tok/s | – |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 21.2 GB | 71k116k with q8 cache | 51tok/sest. | 3649 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 21.9 GB | 44k70k with q8 cache | 91tok/sest. | 4789 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 21.5 GB | 30k52k with q8 cache | 47tok/sest. | 2680 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 20.4 GB | 22k41k with q8 cache | 15tok/sest. | 630 tok/s | chat |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 71tok/sest. | 3466 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 22.1 GB | 14k26k with q8 cache | 64tok/sest. | 3465 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | fits | 21.6 GB | 12k23k with q8 cache | 14tok/sest. | 431 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 24tok/sest. | 1272 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 32tok/sest. | 1610 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q5_K_M | fits | 20.1 GB | 39k74k with q8 cache | 15tok/sest. | 566 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 20.4 GB | 22k41k with q8 cache | 15tok/sest. | 630 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | fits | 21.6 GB | 12k23k with q8 cache | 14tok/sest. | 451 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 51k93k with q8 cache | 20tok/sest. | 1045 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 18tok/sest. | 971 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 92k128k with q8 cache | 32tok/sest. | 1700 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 32tok/sest. | 1700 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 18tok/sest. | 978 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 65tok/sest. | 3242 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 95k173k with q8 cache | 31tok/sest. | 1588 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 80k128k with q8 cache | 29tok/sest. | 1576 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 37tok/sest. | 1951 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 128tok/sest. | 11389 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 118k128k with q8 cache | 41tok/sest. | 1755 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.4 GB | – | 16tok/sest. | 1080 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.6 GB | – | 20tok/sest. | 2561 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.8 GB | – | 24tok/sest. | 1440 tok/s | chat |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.8 GB | – | 6tok/sest. | 514 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.6 GB | – | 26tok/sest. | 3221 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 21tok/sest. | 3979 tok/s | chat, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 46tok/sest. | 3925 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 43.2 GB | – | 2tok/sest. | 149 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 | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 60.5 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4070 Super
- Memory
- 12 GB GDDR6X
- Memory bus
- 192-bit
- Memory bandwidth
- 504 GB/s
- FP16 compute
- 71 TFLOPS
- Software
- CUDA
- Board power
- 220 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16