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 128k context it runs 13 of the 125 open models we track fully in memory; the most capable is Gemma 4 12B at Q4_K_M, at about 33 tok/s (estimated). We have no current price for the NVIDIA GeForce RTX 4070 in the UK.
Updated . Speeds are estimates; how they are worked out.
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 it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q4_K_M | fits | 10.4 GB | 174k256k with q8 cache | 33tok/sest. | 395 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q4_K_M | fits | 10.8 GB | 144k238k with q8 cache | 31tok/sest. | 470 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.7 GB | 174k256k with q8 cache | 35tok/sest. | 732 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q5_K_M | fits | 10.1 GB | 128k | 34tok/sest. | 659 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.4 GB | 32k | 146tok/sest. | 1980 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.7 GB | 256k | 128tok/sest. | 2640 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.3 GB | 256k | 102tok/sest. | 1688 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.7 GB | 128k | 55tok/sest. | 885 tok/s | chat, coding, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 8.8 GB | 190k319k with q8 cache | 39tok/sest. | 724 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.2 GB | 128k | 38tok/sest. | 476 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 9.8 GB | 171k256k with q8 cache | 35tok/sest. | 732 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q6_K | fits | 11.0 GB | 128k | 30tok/sest. | 610 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q6_K | fits | 11.0 GB | 32k | 30tok/sest. | 587 tok/s | chat, coding, agents, long documents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 24.9 GB | – | 3tok/sest. | 106 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 25.3 GB | – | 3tok/sest. | 105 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 29.3 GB | – | 3tok/sest. | 94 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 24.2 GB | – | 11tok/sest. | 519 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 25.2 GB | – | 3tok/sest. | 105 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 19.6 GB | – | 11tok/sest. | 694 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 24.5 GB | – | 11tok/sest. | 516 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 25.1 GB | – | 5tok/sest. | 241 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | – | 2tok/sest. | 84 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 23.9 GB | – | 17tok/sest. | 702 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.5 GB | – | 15tok/sest. | 356 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 15.3 GB | – | 14tok/sest. | 512 tok/s | chat, coding, agents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 30.7 GB | – | 3tok/sest. | 138 tok/s | chat |
| Gemma 3 27B | Q4_K_M | offload | 27.3 GB | – | 3tok/sest. | 125 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | – | 2tok/sest. | 84 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 29.1 GB | 18k34k with q8 cache | 3tok/sest. | 114 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 29.8 GB | 14k26k with q8 cache | 3tok/sest. | 96 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 24.1 GB | 41k74k with q8 cache | 4tok/sest. | 158 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 24.1 GB | 40k | 4tok/sest. | 158 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 34.7 GB | 12k16k with q8 cache | 2tok/sest. | 92 tok/s | chat |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 23.3 GB | 42k76k with q8 cache | 4tok/sest. | 163 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 26.6 GB | 34k62k with q8 cache | 3tok/sest. | 138 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | UD-Q4_K_M | offload | 12.4 GB | 108k125k with q8 cache | 18tok/sest. | 833 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q4_K_M | offload | 22.0 GB | 46k84k with q8 cache | 4tok/sest. | 180 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q4_K_M | offload | 11.5 GB | 125k128k with q8 cache | 49tok/sest. | 1016 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q4_K_M | offload | 12.2 GB | 110k128k with q8 cache | 20tok/sest. | 197 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q4_K_M | offload | 12.8 GB | 104k128k with q8 cache | 16tok/sest. | 292 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-4bit | offload | 13.0 GB | 32k | 15tok/sest. | 194 tok/s | chat, coding |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | offload | 15.1 GB | 24k40k with q8 cache | 14tok/sest. | 537 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q4_K_M | offload | 13.4 GB | 104k128k with q8 cache | 14tok/sest. | 339 tok/s | chat, coding |
| granite 4.2 3b IBM | Q4_K_M | offload | 13.6 GB | 101k128k with q8 cache | 13tok/sest. | 342 tok/s | chat, coding, agents |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 16.3 GB | – | 12tok/sest. | 514 tok/s | chat, coding, agents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q4_K_M | offload | 16.4 GB | 80k145k with q8 cache | 7tok/sest. | 294 tok/s | chat, coding, agents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 17.4 GB | – | 7tok/sest. | 160 tok/s | chat |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 19.3 GB | – | 5tok/sest. | 129 tok/s | – |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q4_K_M | offload | 22.0 GB | 46k84k with q8 cache | 4tok/sest. | 180 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 25.7 GB | – | 4tok/sest. | 332 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | offload | 23.3 GB | 42k76k with q8 cache | 4tok/sest. | 163 tok/s | chat, coding |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 29.1 GB | 18k34k with q8 cache | 3tok/sest. | 114 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 28.8 GB | – | 3tok/sest. | 100 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 33.8 GB | 12k22k with q8 cache | 2tok/sest. | 82 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 34.8 GB | – | 2tok/sest. | 84 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 34.8 GB | – | 2tok/sest. | 84 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 34.8 GB | – | 2tok/sest. | 84 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 34.8 GB | – | 2tok/sest. | 84 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.4 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.0 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 43.6 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.5 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 49.7 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 64.4 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 41.7 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 66.7 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 49.7 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 51.9 GB | – | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 51.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.1 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.2 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 81.1 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 157.8 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 166.6 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 115.2 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 249.0 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 83.7 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 248.2 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 90.1 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.0 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 394.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 432.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 758.7 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 101.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 147.7 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 256.1 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.2 GB | – | – | – | – |
| granite 4.2 30b IBM | Q4_K_M | won't run | 50.2 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?
- Gemma 4 12B (Q4_K_M) fits fully in its memory at 128k context and generates at about 33 tok/s, an estimate from its memory bandwidth. 13 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 102 GB at 128k context, more than the NVIDIA GeForce RTX 4070 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 4070 cost in the UK?
- We have no current price for the NVIDIA GeForce RTX 4070 in the UK.
Speeds on this page are for 128k context. See the best hardware for local AI at every budget.