AMD Radeon RX 9070 XT
16 GB · 640 GB/s · 304 W
In short
The AMD Radeon RX 9070 XT has 16 GB of GDDR6 memory with 640 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 29 of the 113 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 65 tok/s (estimated). The best new price for the AMD Radeon RX 9070 XT in Germany is 778 € at Amazon; used, it starts at 800 € (asking price).
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.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonASUS Prime Radeon RX 9070 XT White OC Edition 16GB GDDR6 Gaming Graphics | New | 778 € | In stock | 12 h ago | Buy |
| eBayPowerColor Reaper Radeon RX 9070 XT 16GB | New | 799 € | In stock | 2 h ago | Buy |
| eBayASRock Grafikkarte AMD Radeon RX 9070 XT Steel Legend 16GB GDDR6 | used, asking price | 800 €+ 6 € delivery | In stock | 2 h ago | Buy |
| AmazonXFX Swift AMD Radeon RX 9070XT Gaming Edition Triple Fan with 16GB GDDR6 HDMI | New | 835 € | In stock | 12 h ago | Buy |
| eBay** XFX Mercury AMD Radeon RX 9070 XT OC White Gaming Edition with RGB 16GB ** | used, asking price | 825 €+ 10 € delivery | In stock | 2 h ago | Buy |
| eBayAsus PRIME Radeon RX 9070 XT 16GB Grafikkarte | New | 830 €+ 6 € delivery | In stock | 2 h ago | Buy |
| AmazonXFX Swift AMD Radeon RX 9070XT White Triple Fan Gaming Edition with 16GB GDDR6 | New | 840 € | In stock | 12 h ago | Buy |
| AmazonSapphire Pulse AMD Radeon RX 9070 XT Gaming 16GB Dual HDMI / Dual DP | New | 856 € | In stock | 12 h ago | Buy |
| AmazonASUS Prime Radeon RX 9070 XT OC Edition 16GB GDDR6 Gaming Graphics Card | New | 888 € | In stock | 4 min ago | Buy |
| eBayGrafikkarte Asus PRIME Radeon RX 9070 XT 16GB Grafikkarte | New | 885 €+ 7 € delivery | In stock | 2 h ago | Buy |
| AmazonGigabyte Radeon RX 9070 XT Gaming OC 16G Graphics Card | New | 896 € | In stock | 13 h ago | Buy |
| eBayXFX Radeon RX 9070 XT Swift Gaming 16GB GDDR6 | New | 903 € | In stock | 2 h ago | Buy |
| eBaySapphire Nitro+ AMD Radeon RX 9070 XT OC Dual DP 16GB GDDR6 Grafikkarte | used, asking price | 900 €+ 8 € delivery | In stock | 2 h ago | Buy |
| AmazonSapphire Pure AMD Radeon RX 9070 XT Gaming OC 16GB Dual HDMI / Dual DP | New | 919 € | In stock | 12 h ago | Buy |
| eBay16GB Asus AMD Radeon RX 9070 XT Prime OC Edition GDDR6 Gaming Grafikkarte | used, asking price | 915 €+ 8 € delivery | In stock | 5 h ago | Buy |
| eBayGigabyte Radeon RX 9070 XT Gaming OC 16 GB GDDR6 PCIe 5.0 x16 | New | 925 € | In stock | 2 h ago | Buy |
| eBayPowercolor Radeon RX9070XT Hellhound OC 16GB | New | 935 € | In stock | 2 h ago | Buy |
| AmazonGigabyte AORUS Radeon RX 9070 XT Elite 16G Graphics Card | New | 959 € | In stock | 12 h ago | Buy |
| eBay16GB PowerColor RX9070XT 16G-A Radeon RX 9070 XT Reaper GDDR6 9070XT AMD 2970MHz | New | 963 € | In stock | 2 h ago | Buy |
| eBayAsRock Radeon RX 9070 XT Steel Legend Dark AMD 16GB GDDR6 RX9070XT | New | 963 € | In stock | 2 h ago | Buy |
| AmazonGigabyte Radeon RX 9070 XT Gaming OC Ice 16G Graphics Card | New | 965 € | In stock | 12 h ago | Buy |
| eBayGrafikkarte AMD Sapphire Radeon RX 9070 XT Pulse 16GB GDDR6 RAM Gaming HDMI | New | 959 €+ 7 € delivery | In stock | 2 h ago | Buy |
| eBay16GB XFX RX-97TRGBBB9 Mercury Radeon RX9070XT OC Gaming Edition with RGB | New | 969 € | In stock | 2 h ago | Buy |
| AmazonSapphire Nitro+ AMD Radeon RX 9070 XT Gaming OC 16GB DUAL HDMI/DUAL DP | New | 969 € | In stock | 12 h ago | Buy |
| eBayASRock AMD Radeon RX 9070 XT Steel Legend DARK 16GB GDDR6 PCIe 5.0 1x HDMI 3x DP | New | 960 €+ 12 € delivery | In stock | 2 h ago | Buy |
| eBayGrafikkarte Sapphire PULSE Radeon RX 9070 XT 16GB GDDR6 HDMI 2x DP AMD GPU | New | 977 € | In stock | 2 h ago | Buy |
| eBayAsrock Steel Legend Radeon RX 9070 XT AMD 16 GB GDDR6 | New | 979 € | In stock | 2 h ago | Buy |
| AmazonASUS Prime Radeon RX 9070 XT White OC Edition Graphics Card | New | 979 € | In stock | 12 h ago | Buy |
| eBayASRock AMD Radeon RX 9070 XT CHALLENGER 16GB GDDR6 Grafikkarte 1x HDMI 3x DP Neu | New | 970 €+ 10 € delivery | In stock | 2 h ago | Buy |
| eBay16GB PowerColor RX9070XT 16G-L/OC Hellhound Radeon RX 9070 XT OC AMD GDDR6 9070X | New | 982 € | In stock | 2 h ago | Buy |
| AmazonSapphire Nitro+ AMD Radeon RX 9070 XT 16 GB Crimson Desert Version Gaming OC | New | 993 € | In stock | 12 h ago | Buy |
| eBayAcer Nitro Radeon RX 9070 XT OC | used, asking price | 1.017 € | In stock | 2 h ago | Buy |
| eBayAcer Predator BiFrost Radeon RX 9070 XT OC | used, asking price | 1.017 € | In stock | 2 h ago | Buy |
| AmazonAsrock Taichi Radeon Rx 9070 XT White 16GB Oc Amd Gddr6 | New | 1.074 € | In stock | 12 h ago | Buy |
| eBayAsus PRIME Radeon RX 9070 XT 16GB WHITE Grafikkarte | used, asking price | 1.100 €+ 8 € delivery | In stock | 2 h ago | Buy |
Used on eBay: median asking price 862 €, most between 806 € and 988 € (6 listings, 2026-10-15).
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
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 |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.0 GB | 106k128k with q8 cache | 65tok/sest. | 5867 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 13.6 GB | 106k171k with q8 cache | 26tok/sest. | 2553 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.9 GB | 147k243k with q8 cache | 33tok/sest. | 3181 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 14.4 GB | 37k40k with q8 cache | 25tok/sest. | 1589 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q5_K_M | fits | 14.9 GB | 33k61k with q8 cache | 24tok/sest. | 1767 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.6 GB | 42k78k with q8 cache | 26tok/sest. | 2620 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.6 GB | 40k | 26tok/sest. | 2620 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.2 GB | 256k | 63tok/sest. | 5952 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.6 GB | 43k78k with q8 cache | 26tok/sest. | 2531 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.7 GB | 35k64k with q8 cache | 24tok/sest. | 2410 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.5 GB | 128k | 38tok/sest. | 3996 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.9 GB | 113k125k with q8 cache | 79tok/sest. | 13072 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.1 GB | 63k114k with q8 cache | 32tok/sest. | 2769 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.9 GB | 32k | 377tok/sest. | 28469 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.1 GB | 256k | 285tok/sest. | 26742 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.7 GB | 256k | 190tok/sest. | 12749 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.6 GB | 128k | 124tok/sest. | 10710 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.8 GB | 128k | 86tok/sest. | 6396 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.5 GB | 128k | 72tok/sest. | 7245 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.5 GB | 32k | 72tok/sest. | 6643 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.5 GB | 118k128k with q8 cache | 67tok/sest. | 9438 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-6bit | fits | 14.8 GB | 42k70k with q8 cache | 60tok/sest. | 7092 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.9 GB | 128k | 56tok/sest. | 4641 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 7.1 GB | 128k | 54tok/sest. | 4865 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.3 GB | 113k128k with q8 cache | 35tok/sest. | 3130 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.6 GB | 113k128k with q8 cache | 31tok/sest. | 2179 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 12.9 GB | 49k89k with q8 cache | 27tok/sest. | 2769 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.2 GB | 64k | 27tok/sest. | 2179 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.6 GB | 43k78k with q8 cache | 26tok/sest. | 2531 tok/s | chat, coding |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 18.5 GB | – | 9tok/sest. | 977 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.8 GB | – | 11tok/sest. | 1585 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 18.8 GB | – | 9tok/sest. | 968 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 21.3 GB | – | 6tok/sest. | 803 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.1 GB | – | 15tok/sest. | 1789 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.9 GB | – | 30tok/sest. | 6350 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 18.7 GB | – | 9tok/sest. | 970 tok/s | – |
| Gemma 4 26B-A4B | UD-Q4_K_M | offload | 17.6 GB | – | 34tok/sest. | 6388 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.2 GB | – | 29tok/sest. | 6307 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 19.7 GB | – | 19tok/sest. | 3512 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 19.3 GB | 6k11k with q8 cache | 8tok/sest. | 1004 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 14tok/sest. | 5916 tok/s | – |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.3 GB | – | 26tok/sest. | 4751 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 21.3 GB | – | 16tok/sest. | 2965 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.4 GB | – | 4tok/sest. | 494 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 19.3 GB | – | 8tok/sest. | 1011 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 19.3 GB | 6k11k with q8 cache | 8tok/sest. | 1004 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.5 GB | – | 4tok/sest. | 566 tok/s | – |
| Phi-4 14B Microsoft | Q4_K_M | offload | 15.5 GB | 16k | 20tok/sest. | 1576 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 17.8 GB | 1k2k with q8 cache | 29tok/sest. | 6612 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 15.4 GB | 31k57k with q8 cache | 22tok/sest. | 1485 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 19.3 GB | 6k11k with q8 cache | 8tok/sest. | 1020 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 19.3 GB | 6k11k with q8 cache | 8tok/sest. | 1020 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 19.3 GB | 6k11k with q8 cache | 8tok/sest. | 1020 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 19.3 GB | 6k11k with q8 cache | 8tok/sest. | 1004 tok/s | chat |
| granite 4.2 30b IBM | Q4_K_M | offload | 25.8 GB | – | 4tok/sest. | 671 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.9 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.3 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.9 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.3 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.0 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.6 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.9 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.0 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.6 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.8 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.3 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.6 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.8 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.7 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.7 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.3 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.1 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 135.7 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 66.0 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.3 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.1 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.7 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.6 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.1 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.3 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.7 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.7 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.7 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.6 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.6 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 124.0 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 251.5 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon RX 9070 XT
- Memory
- 16 GB GDDR6
- Memory bus
- 256-bit
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 195 TFLOPS
- Software
- ROCm
- Board power
- 304 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the AMD Radeon RX 9070 XT have for AI models?
- The AMD Radeon RX 9070 XT 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 XT can run locally?
- gpt-oss 20B (MXFP4) fits fully in its memory at 32k context and generates at about 65 tok/s, an estimate from its memory bandwidth. 29 of the 113 models we track fit at that context.
- Can the AMD Radeon RX 9070 XT run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the AMD Radeon RX 9070 XT and system RAM can hold.
- How much does the AMD Radeon RX 9070 XT cost in Germany?
- The best new price for the AMD Radeon RX 9070 XT in Germany is 778 € at Amazon; used, it starts at 800 € (asking price).
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.