NVIDIA GeForce RTX 4070
12 GB · 504.2 GB/s · 200 W
In short
The NVIDIA GeForce RTX 4070 has 12 GB of GDDR6X memory with 504.2 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 21 of the 125 open models we track fully in memory; the most capable is Gemma 4 12B at Q5_K_M, at about 32 tok/s (estimated). We have no current price for the NVIDIA GeForce RTX 4070 in Germany.
Updated . Speeds are estimates; how they are worked out.
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 it runs
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 |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q5_K_M | fits | 10.2 GB | 118k190k with q8 cache | 32tok/sest. | 454 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q6_K | fits | 10.1 GB | 99k165k with q8 cache | 32tok/sest. | 556 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 174k256k with q8 cache | 47tok/sest. | 963 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 91k128k with q8 cache | 31tok/sest. | 728 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | UD-Q6_K | fits | 10.7 GB | 77k125k with q8 cache | 46tok/sest. | 1554 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.3 GB | 32k | 234tok/sest. | 3446 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 191tok/sest. | 3906 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 138tok/sest. | 2130 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.6 GB | 128k | 83tok/sest. | 1427 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q5_K_M | fits | 11.3 GB | 70k106k with q8 cache | 62tok/sest. | 1440 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.2 GB | 128k | 57tok/sest. | 804 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.2 GB | 190k319k with q8 cache | 57tok/sest. | 987 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.4 GB | 171k256k with q8 cache | 46tok/sest. | 963 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.5 GB | 124k128k with q8 cache | 45tok/sest. | 975 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.5 GB | 32k | 45tok/sest. | 917 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q4_K_M | fits | 9.3 GB | 110k128k with q8 cache | 35tok/sest. | 312 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.4 GB | 87k128k with q8 cache | 35tok/sest. | 612 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 9.7 GB | 84k128k with q8 cache | 34tok/sest. | 632 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q6_K | fits | 10.4 GB | 80k128k with q8 cache | 31tok/sest. | 462 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.0 GB | 67k122k with q8 cache | 29tok/sest. | 606 tok/s | chat, coding, agents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.3 GB | 32k | 29tok/sest. | 326 tok/s | chat, coding |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 20.5 GB | – | 5tok/sest. | 138 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 20.9 GB | – | 4tok/sest. | 137 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 23.9 GB | – | 4tok/sest. | 117 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 22.6 GB | – | 17tok/sest. | 794 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 20.8 GB | – | 5tok/sest. | 137 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 17.9 GB | – | 16tok/sest. | 907 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.9 GB | – | 16tok/sest. | 789 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 21.4 GB | – | 8tok/sest. | 403 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 126 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 23.1 GB | – | 20tok/sest. | 969 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 13.4 GB | – | 27tok/sest. | 797 tok/s | chat, coding, agents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.6 GB | – | 19tok/sest. | 572 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.4 GB | – | 6tok/sest. | 275 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.5 GB | – | 2tok/sest. | 57 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 21.9 GB | – | 4tok/sest. | 150 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 126 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.6 GB | – | 2tok/sest. | 70 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 18.7 GB | 18k34k with q8 cache | 6tok/sest. | 199 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 19.5 GB | 14k26k with q8 cache | 5tok/sest. | 171 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 14.8 GB | 41k74k with q8 cache | 10tok/sest. | 313 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 14.8 GB | 40k | 10tok/sest. | 313 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 21.9 GB | 12k16k with q8 cache | 4tok/sest. | 163 tok/s | chat |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 14.4 GB | 42k76k with q8 cache | 10tok/sest. | 314 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 16.2 GB | 34k62k with q8 cache | 8tok/sest. | 272 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q4_K_M | offload | 13.7 GB | 46k84k with q8 cache | 12tok/sest. | 352 tok/s | chat, coding |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | offload | 12.8 GB | 24k40k with q8 cache | 30tok/sest. | 920 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 14.0 GB | – | 23tok/sest. | 871 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q4_K_M | offload | 13.7 GB | 46k84k with q8 cache | 12tok/sest. | 352 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | offload | 14.4 GB | 42k76k with q8 cache | 10tok/sest. | 314 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 14.5 GB | – | 10tok/sest. | 268 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 20.4 GB | – | 9tok/sest. | 642 tok/s | chat |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 18.1 GB | – | 6tok/sest. | 148 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 18.7 GB | 18k34k with q8 cache | 6tok/sest. | 199 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 21.4 GB | 12k22k with q8 cache | 4tok/sest. | 150 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 127 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 127 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 127 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 126 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 24.5 GB | – | 3tok/sest. | 127 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 33.9 GB | – | 2tok/sest. | 83 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.7 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 41.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.6 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 61.8 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 39.9 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.5 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 160.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 71.8 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 224.9 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 388.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.9 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4070
- Memory
- 12 GB GDDR6X
- Memory bus
- 192-bit
- Memory bandwidth
- 504.2 GB/s
- FP16 compute
- 29.146 TFLOPS
- Software
- CUDA
- Board power
- 200 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 4070 have for AI models?
- The NVIDIA GeForce RTX 4070 has 12 GB of GDDR6X memory with 504.2 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 4070 can run locally?
- Gemma 4 12B (Q5_K_M) fits fully in its memory at 64k context and generates at about 32 tok/s, an estimate from its memory bandwidth. 21 of the 125 models we track fit at that context.
- Can the NVIDIA GeForce RTX 4070 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 97 GB at 64k context, more than the NVIDIA GeForce RTX 4070 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 4070 cost in Germany?
- We have no current price for the NVIDIA GeForce RTX 4070 in Germany.
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.