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 32k context it runs 28 of the 125 open models we track fully in memory; the most capable is Gemma 4 12B at Q6_K, at about 29 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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q6_K | fits | 10.8 GB | 59k100k with q8 cache | 29tok/sest. | 491 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 47k79k with q8 cache | 29tok/sest. | 611 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q5_K_M | fits | 10.8 GB | 35k65k with q8 cache | 29tok/sest. | 504 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q5_K_M | fits | 10.8 GB | 35k40k with q8 cache | 29tok/sest. | 504 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 174k256k with q8 cache | 56tok/sest. | 1144 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q5_K_M | fits | 10.8 GB | 36k66k with q8 cache | 29tok/sest. | 486 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | fits | 11.0 GB | 34k62k with q8 cache | 29tok/sest. | 463 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.4 GB | 91k128k with q8 cache | 34tok/sest. | 768 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.8 GB | 43k75k with q8 cache | 70tok/sest. | 2512 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 11.0 GB | 34k63k with q8 cache | 29tok/sest. | 532 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.8 GB | 32k | 335tok/sest. | 5471 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 254tok/sest. | 5139 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 168tok/sest. | 2450 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.5 GB | 128k | 110tok/sest. | 2058 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.7 GB | 128k | 77tok/sest. | 1229 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q5_K_M | fits | 10.7 GB | 70k106k with q8 cache | 73tok/sest. | 1814 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.9 GB | 190k319k with q8 cache | 73tok/sest. | 1207 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.4 GB | 124k128k with q8 cache | 64tok/sest. | 1392 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.4 GB | 32k | 64tok/sest. | 1277 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.2 GB | 171k256k with q8 cache | 54tok/sest. | 1144 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.8 GB | 87k128k with q8 cache | 50tok/sest. | 892 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 7.0 GB | 84k128k with q8 cache | 48tok/sest. | 935 tok/s | chat, coding, agents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.5 GB | 67k122k with q8 cache | 44tok/sest. | 894 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q4_K_M | fits | 7.9 GB | 110k128k with q8 cache | 42tok/sest. | 419 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.8 GB | 32k | 33tok/sest. | 444 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.2 GB | 52k90k with q8 cache | 31tok/sest. | 601 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q5_K_M | fits | 10.8 GB | 36k66k with q8 cache | 29tok/sest. | 486 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q6_K | fits | 11.0 GB | 34k63k with q8 cache | 29tok/sest. | 532 tok/s | chat, coding |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 18.4 GB | – | 6tok/sest. | 161 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 18.7 GB | – | 6tok/sest. | 160 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 21.2 GB | – | 4tok/sest. | 134 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.8 GB | – | 22tok/sest. | 1060 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 18.6 GB | – | 6tok/sest. | 160 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 17.1 GB | – | 20tok/sest. | 1060 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.1 GB | – | 21tok/sest. | 1054 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 19.6 GB | – | 13tok/sest. | 581 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 166 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 22.7 GB | – | 22tok/sest. | 1187 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 12.5 GB | – | 41tok/sest. | 1065 tok/s | chat, coding, agents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 22tok/sest. | 811 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 11tok/sest. | 494 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.3 GB | – | 3tok/sest. | 84 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 167 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 166 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.4 GB | – | 3tok/sest. | 96 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 13.6 GB | 18k34k with q8 cache | 13tok/sest. | 305 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 14.3 GB | 14k26k with q8 cache | 11tok/sest. | 266 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 15.4 GB | 12k16k with q8 cache | 9tok/sest. | 256 tok/s | chat |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | offload | 11.7 GB | 24k40k with q8 cache | 57tok/sest. | 1344 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 12.9 GB | – | 37tok/sest. | 1263 tok/s | chat, coding, agents |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 17.7 GB | – | 17tok/sest. | 1086 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 13.1 GB | – | 14tok/sest. | 384 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 13.6 GB | 18k34k with q8 cache | 13tok/sest. | 305 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 15.3 GB | 12k22k with q8 cache | 9tok/sest. | 241 tok/s | chat |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.5 GB | – | 6tok/sest. | 159 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 169 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 169 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 169 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 166 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 22.3 GB | – | 4tok/sest. | 147 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 25.7 GB | – | 3tok/sest. | 113 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.8 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 | 75.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.8 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.2 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.5 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 39.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.2 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.0 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 81.6 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 65.9 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.2 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.6 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.5 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.0 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 70.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 123.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.6 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 (Q6_K) fits fully in its memory at 32k context and generates at about 29 tok/s, an estimate from its memory bandwidth. 28 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 94 GB at 32k 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 32k context. See the best hardware for local AI at every budget.