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 45 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q4_K_M, at about 14 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 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 | Q4_K_M | fits | 21.9 GB | 77k136k with q8 cache | 14tok/sest. | 192 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | fits | 21.3 GB | 86k150k with q8 cache | 15tok/sest. | 192 tok/s | chat |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | fits | 21.2 GB | 87k152k with q8 cache | 15tok/sest. | 192 tok/s | chat |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 22.6 GB | 71k116k with q8 cache | 39tok/sest. | 1181 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | fits | 21.8 GB | 80k139k with q8 cache | 29tok/sest. | 572 tok/s | chat, coding, agents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 46tok/sest. | 883 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 22tok/sest. | 454 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 27tok/sest. | 556 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q4_K_M | fits | 22.3 GB | 70k128k with q8 cache | 14tok/sest. | 215 tok/s | chat |
| Ministral 3 14B Mistral AI | Q6_K | fits | 21.8 GB | 70k127k with q8 cache | 14tok/sest. | 266 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q6_K | fits | 22.8 GB | 40k | 14tok/sest. | 233 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 92k128k with q8 cache | 17tok/sest. | 367 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 17tok/sest. | 367 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | fits | 22.3 GB | 16k | 14tok/sest. | 234 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 47tok/sest. | 963 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 95k173k with q8 cache | 17tok/sest. | 363 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 80k128k with q8 cache | 16tok/sest. | 336 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 31tok/sest. | 728 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 44tok/sest. | 1554 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 118k128k with q8 cache | 21tok/sest. | 395 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.7 GB | 32k | 234tok/sest. | 3446 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.0 GB | 256k | 191tok/sest. | 3906 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.6 GB | 256k | 138tok/sest. | 2130 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.0 GB | 128k | 83tok/sest. | 1427 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.6 GB | 128k | 57tok/sest. | 804 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.6 GB | 458k767k with q8 cache | 57tok/sest. | 987 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.4 GB | 128k | 52tok/sest. | 1440 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.8 GB | 256k | 46tok/sest. | 963 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.9 GB | 128k | 45tok/sest. | 975 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.9 GB | 32k | 45tok/sest. | 917 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 19.2 GB | 128k | 37tok/sest. | 990 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.0 GB | 128k | 35tok/sest. | 990 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.8 GB | 128k | 35tok/sest. | 612 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 10.1 GB | 128k | 34tok/sest. | 632 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.4 GB | 170k256k with q8 cache | 29tok/sest. | 606 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.7 GB | 32k | 29tok/sest. | 326 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | fits | 20.8 GB | 88k128k with q8 cache | 28tok/sest. | 890 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.5 GB | 128k | 26tok/sest. | 462 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.3 GB | 128k | 25tok/sest. | 312 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.9 GB | 64k | 22tok/sest. | 312 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.4 GB | 105k128k with q8 cache | 18tok/sest. | 395 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.4 GB | 95k173k with q8 cache | 17tok/sest. | 363 tok/s | chat, coding |
| Muse Glimmer 30B meta-models | Q5_K_M | fits | 21.1 GB | 128k | 15tok/sest. | 193 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | fits | 21.8 GB | 68k126k with q8 cache | 14tok/sest. | 212 tok/s | chat, coding |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q6_K | fits | 21.8 GB | 70k127k with q8 cache | 14tok/sest. | 266 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.1 GB | – | 11tok/sest. | 285 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 13tok/sest. | 623 tok/s | chat |
| Gemma 4 31B | Q4_K_M | offload | 24.3 GB | 45k89k with q8 cache | 10tok/sest. | 168 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.3 GB | – | 15tok/sest. | 286 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 23.0 GB | 56k87k with q8 cache | 56tok/sest. | 1147 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 | 52tok/sest. | 1138 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.2 GB | – | 15tok/sest. | 710 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.8 GB | 51k93k with q8 cache | 9tok/sest. | 179 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 23.5 GB | 3k4k with q8 cache | 61tok/sest. | 1395 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.0 GB | – | 35tok/sest. | 786 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.8 GB | 44k79k with q8 cache | 16tok/sest. | 392 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.9 GB | 12k23k with q8 cache | 3tok/sest. | 75 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.8 GB | 51k93k with q8 cache | 9tok/sest. | 179 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.0 GB | 12k23k with q8 cache | 3tok/sest. | 93 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 24.8 GB | 51k93k with q8 cache | 9tok/sest. | 181 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 24.8 GB | 40k | 9tok/sest. | 181 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 24.8 GB | 40k | 9tok/sest. | 181 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 24.8 GB | 51k93k with q8 cache | 9tok/sest. | 179 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 24.9 GB | 33k59k with q8 cache | 9tok/sest. | 182 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 34.3 GB | 19k35k with q8 cache | 3tok/sest. | 112 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 | Q4_K_M | won't run | 62.2 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 | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 61.1 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.3 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 93.2 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 225.3 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.6 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 389.3 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.9 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.8 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.3 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.2 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 93.2 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?
- Qwen 3.8 27B (Q4_K_M) fits fully in its memory at 64k context and generates at about 14 tok/s, an estimate from its memory bandwidth. 45 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.