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 64k context it runs 58 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q6_K, 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q6_K | fits | 28.0 GB | 98k172k with q8 cache | 12tok/sest. | 185 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 26.8 GB | 116k204k with q8 cache | 13tok/sest. | 185 tok/s | chat |
| Gemma 4 31B | Q5_K_M | fits | 27.6 GB | 97k179k with q8 cache | 13tok/sest. | 169 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 30.3 GB | 68k107k with q8 cache | 55tok/sest. | 1111 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 26.7 GB | 117k206k with q8 cache | 13tok/sest. | 185 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 28.1 GB | 153k245k with q8 cache | 37tok/sest. | 1138 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.9 GB | 85k133k with q8 cache | 55tok/sest. | 1111 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 28.0 GB | 106k183k with q8 cache | 28tok/sest. | 551 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 29.7 GB | 68k124k with q8 cache | 12tok/sest. | 182 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q5_K_M | fits | 30.2 GB | 78k101k with q8 cache | 64tok/sest. | 1370 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 30.2 GB | 78k107k with q8 cache | 88tok/sest. | 893 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 52tok/sest. | 851 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 27.9 GB | 89k159k with q8 cache | 25tok/sest. | 398 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 25tok/sest. | 437 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 30tok/sest. | 535 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q6_K | fits | 27.7 GB | 95k128k with q8 cache | 13tok/sest. | 207 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 29.7 GB | 68k124k with q8 cache | 12tok/sest. | 182 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 25.0 GB | 97k176k with q8 cache | 14tok/sest. | 256 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.3 GB | 40k | 13tok/sest. | 224 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 128k | 19tok/sest. | 354 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 19tok/sest. | 354 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.7 GB | 16k | 12tok/sest. | 225 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 53tok/sest. | 928 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 149k256k with q8 cache | 19tok/sest. | 350 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 125k128k with q8 cache | 18tok/sest. | 324 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 35tok/sest. | 701 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 49tok/sest. | 1497 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 128k | 23tok/sest. | 380 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.9 GB | 32k | 263tok/sest. | 3319 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.2 GB | 256k | 215tok/sest. | 3763 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.8 GB | 256k | 156tok/sest. | 2052 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.2 GB | 128k | 93tok/sest. | 1375 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.8 GB | 128k | 64tok/sest. | 775 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.8 GB | 639k1024k with q8 cache | 64tok/sest. | 951 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.6 GB | 128k | 58tok/sest. | 1387 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 8.0 GB | 256k | 52tok/sest. | 928 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 8.1 GB | 128k | 51tok/sest. | 940 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 8.1 GB | 32k | 51tok/sest. | 884 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 19.4 GB | 128k | 41tok/sest. | 954 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.2 GB | 128k | 40tok/sest. | 954 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 10.0 GB | 128k | 39tok/sest. | 590 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 10.3 GB | 128k | 38tok/sest. | 609 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.6 GB | 239k256k with q8 cache | 33tok/sest. | 583 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.9 GB | 32k | 32tok/sest. | 314 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.7 GB | 128k | 30tok/sest. | 445 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q6_K | fits | 26.4 GB | 111k128k with q8 cache | 30tok/sest. | 857 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.5 GB | 128k | 28tok/sest. | 300 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 15.1 GB | 64k | 24tok/sest. | 300 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.6 GB | 128k | 21tok/sest. | 380 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.6 GB | 149k256k with q8 cache | 19tok/sest. | 350 tok/s | chat, coding |
| Muse Glimmer 30B meta-models | Q6_K | fits | 24.4 GB | 128k | 14tok/sest. | 186 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 25.0 GB | 97k176k with q8 cache | 14tok/sest. | 256 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 25.1 GB | 142k248k with q8 cache | 14tok/sest. | 185 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q5_K_M | fits | 27.3 GB | 83k128k with q8 cache | 13tok/sest. | 184 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q5_K_M | fits | 27.3 GB | 40k | 13tok/sest. | 184 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q5_K_M | fits | 27.3 GB | 83k128k with q8 cache | 13tok/sest. | 182 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 28.3 GB | 74k128k with q8 cache | 12tok/sest. | 205 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q6_K | fits | 29.7 GB | 40k | 12tok/sest. | 184 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.3 GB | – | 16tok/sest. | 317 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 17tok/sest. | 684 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.2 GB | – | 10tok/sest. | 328 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.5 GB | – | 22tok/sest. | 319 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.4 GB | – | 3tok/sest. | 90 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 19tok/sest. | 781 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 36.1 GB | 40k | 5tok/sest. | 85 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.2 GB | 41k76k with q8 cache | 5tok/sest. | 105 tok/s | chat |
| granite 4.2 30b IBM | Q4_K_M | offload | 34.5 GB | 48k88k with q8 cache | 6tok/sest. | 126 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.7 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.3 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 62.4 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 61.3 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 383.1 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 61.3 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.7 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.5 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 93.4 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 226.3 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 72.4 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 225.5 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.3 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 389.5 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 427.1 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 441.0 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.5 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.6 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 584.1 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 146.0 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 146.0 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.4 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.9 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 93.4 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 (Q6_K) fits fully in its memory at 64k context and generates at about 12 tok/s, an estimate from its memory bandwidth. 58 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 97 GB at 64k 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 64k context. See the best hardware for local AI at every budget.