AMD Radeon RX 9070
16 GB · 640 GB/s · 220 W
In short
The AMD Radeon RX 9070 has 16 GB of GDDR6 memory with 640 GB/s of bandwidth, which sets how fast it generates text. At 128k context it runs 47 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q5_K_M, at about 12 tok/s (estimated). We have no current price for the AMD Radeon RX 9070 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 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q5_K_M | fits | 29.7 GB | 138k242k with q8 cache | 12tok/sest. | 155 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 28.4 GB | 157k256k with q8 cache | 13tok/sest. | 155 tok/s | chat |
| Gemma 4 31B | Q4_K_M | fits | 29.9 GB | 133k245k with q8 cache | 12tok/sest. | 147 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q5_K_M | fits | 29.2 GB | 173k256k with q8 cache | 43tok/sest. | 755 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q5_K_M | fits | 28.5 GB | 156k256k with q8 cache | 12tok/sest. | 155 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.8 GB | 153k245k with q8 cache | 30tok/sest. | 916 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q5_K_M | fits | 29.1 GB | 180k256k with q8 cache | 43tok/sest. | 755 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 28.6 GB | 159k198k with q8 cache | 20tok/sest. | 356 tok/s | chat, coding, agents, long documents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q4_K_M | fits | 26.4 GB | 256k | 65tok/sest. | 1016 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 37tok/sest. | 593 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 23tok/sest. | 381 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 25tok/sest. | 453 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q4_K_M | fits | 27.9 GB | 128k | 13tok/sest. | 190 tok/s | chat |
| Ministral 3 14B Mistral AI | Q4_K_M | fits | 29.7 GB | 132k241k with q8 cache | 12tok/sest. | 178 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.2 GB | 128k | 13tok/sest. | 230 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.2 GB | 40k | 13tok/sest. | 230 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 40tok/sest. | 706 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.5 GB | 149k256k with q8 cache | 13tok/sest. | 233 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q6_K | fits | 29.1 GB | 128k | 12tok/sest. | 209 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 29tok/sest. | 635 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 28tok/sest. | 849 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.2 GB | 128k | 15tok/sest. | 251 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 4.0 GB | 32k | 164tok/sest. | 1907 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 4.3 GB | 256k | 144tok/sest. | 2543 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.9 GB | 256k | 115tok/sest. | 1626 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 7.3 GB | 128k | 62tok/sest. | 852 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.9 GB | 128k | 46tok/sest. | 982 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 9.4 GB | 639k1024k with q8 cache | 44tok/sest. | 698 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.8 GB | 128k | 42tok/sest. | 458 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 10.4 GB | 256k | 39tok/sest. | 706 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 12.2 GB | 128k | 32tok/sest. | 588 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 12.2 GB | 32k | 32tok/sest. | 565 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 21.7 GB | 128k | 29tok/sest. | 617 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 22.4 GB | 128k | 29tok/sest. | 617 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 14.7 GB | 32k | 26tok/sest. | 205 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 15.4 GB | 128k | 25tok/sest. | 363 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.7 GB | 128k | 24tok/sest. | 370 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 16.4 GB | 128k | 23tok/sest. | 199 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.6 GB | 128k | 23tok/sest. | 304 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 18.0 GB | 64k | 21tok/sest. | 199 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 18.5 GB | 239k256k with q8 cache | 20tok/sest. | 355 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q5_K_M | fits | 29.3 GB | 128k | 17tok/sest. | 496 tok/s | chat, coding, agents, long documents |
| Muse Glimmer 30B meta-models | Q6_K | fits | 25.6 GB | 128k | 14tok/sest. | 169 tok/s | – |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 26.0 GB | 128k | 14tok/sest. | 251 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 27.5 GB | 149k256k with q8 cache | 13tok/sest. | 233 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 29.4 GB | 142k248k with q8 cache | 12tok/sest. | 155 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | fits | 29.7 GB | 132k241k with q8 cache | 12tok/sest. | 178 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 44.2 GB | – | 11tok/sest. | 222 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 50.3 GB | – | 11tok/sest. | 461 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 54.1 GB | – | 9tok/sest. | 282 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 42.3 GB | – | 15tok/sest. | 197 tok/s | chat, coding |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 50.3 GB | – | 13tok/sest. | 504 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 35.4 GB | 97k177k with q8 cache | 5tok/sest. | 126 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 31.1 GB | 78k107k with q8 cache | 64tok/sest. | 559 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 31.3 GB | 118k212k with q8 cache | 12tok/sest. | 215 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 52.5 GB | 40k | 2tok/sest. | 46 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 35.4 GB | 97k128k with q8 cache | 5tok/sest. | 126 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 52.5 GB | 41k76k with q8 cache | 2tok/sest. | 62 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 30.4 GB | 40k | 12tok/sest. | 152 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 35.3 GB | 16k | 5tok/sest. | 139 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 34.4 GB | 107k128k with q8 cache | 6tok/sest. | 124 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 35.4 GB | 97k128k with q8 cache | 5tok/sest. | 128 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 35.4 GB | 40k | 5tok/sest. | 128 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 35.4 GB | 40k | 5tok/sest. | 128 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 35.4 GB | 97k128k with q8 cache | 5tok/sest. | 126 tok/s | chat |
| granite 4.2 30b IBM | Q4_K_M | offload | 50.8 GB | 48k88k with q8 cache | 2tok/sest. | 74 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.8 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 65.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 67.3 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.8 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 167.2 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 115.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 84.3 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 248.8 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 90.7 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 395.4 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 433.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 759.3 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 102.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 148.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 256.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.8 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon RX 9070
- Memory
- 16 GB GDDR6
- Memory bus
- 256-bit
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 36.1 TFLOPS
- Software
- ROCm
- Board power
- 220 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the AMD Radeon RX 9070 have for AI models?
- The AMD Radeon RX 9070 has 16 GB of GDDR6 memory with 640 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the AMD Radeon RX 9070 can run locally?
- Qwen 3.8 27B (Q5_K_M) fits fully in its memory at 128k context and generates at about 12 tok/s, an estimate from its memory bandwidth. 47 of the 125 models we track fit at that context.
- Can the AMD Radeon RX 9070 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 103 GB at 128k context, more than the AMD Radeon RX 9070 and system RAM can hold.
- How much does the AMD Radeon RX 9070 cost in the UK?
- We have no current price for the AMD Radeon RX 9070 in the UK.
Speeds on this page are for 128k context. See the best hardware for local AI at every budget.