NVIDIA RTX 6000 Ada Generation
48 GB · 960 GB/s · 300 W
In short
The NVIDIA RTX 6000 Ada Generation has 48 GB of GDDR6 memory with 960 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 63 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 18 tok/s (estimated). We have no current price for the NVIDIA RTX 6000 Ada Generation in Germany.
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.
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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.3 GB | 256k | 18tok/sest. | 599 tok/s | chat, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 41.7 GB | 256k | 70tok/sest. | 1247 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 31.8 GB | 256k | 18tok/sest. | 599 tok/s | chat, long documents |
| Gemma 4 31B | Q8_0 | fits | 37.3 GB | 184k256k with q8 cache | 15tok/sest. | 547 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 39.9 GB | 332k528k with q8 cache | 92tok/sest. | 1226 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 80tok/sest. | 3606 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 31.8 GB | 256k | 18tok/sest. | 599 tok/s | chat, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.5 GB | 256k | 63tok/sest. | 3692 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 80tok/sest. | 3606 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.0 GB | 198k | 41tok/sest. | 1789 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.4 GB | 144k262k with q8 cache | 17tok/sest. | 590 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.1 GB | 256k | 95tok/sest. | 4446 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 39.3 GB | 662k902k with q8 cache | 117tok/sest. | 2896 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.9 GB | 128k | 88tok/sest. | 2760 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.3 GB | 165k256k with q8 cache | 37tok/sest. | 1290 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 42.1 GB | 40k | 14tok/sest. | 305 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 14.2 GB | 256k | 42tok/sest. | 1419 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.0 GB | 256k | 51tok/sest. | 1737 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.2 GB | 128k | 17tok/sest. | 671 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 17tok/sest. | 590 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 42.1 GB | 84k128k with q8 cache | 14tok/sest. | 378 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.4 GB | 205k256k with q8 cache | 24tok/sest. | 830 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 25.7 GB | 40k | 23tok/sest. | 727 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.2 GB | 128k | 32tok/sest. | 1148 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.2 GB | 40k | 32tok/sest. | 1148 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.1 GB | 16k | 21tok/sest. | 730 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 256k | 89tok/sest. | 3011 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.0 GB | 256k | 33tok/sest. | 1136 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.8 GB | 128k | 30tok/sest. | 1050 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 128k | 59tok/sest. | 2275 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.5 GB | 125k | 83tok/sest. | 4856 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.2 GB | 128k | 39tok/sest. | 1233 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.3 GB | 32k | 445tok/sest. | 10769 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 364tok/sest. | 12210 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 263tok/sest. | 6656 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.6 GB | 128k | 158tok/sest. | 4460 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.2 GB | 128k | 108tok/sest. | 2514 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.2 GB | 1024k | 108tok/sest. | 3086 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.0 GB | 128k | 98tok/sest. | 4500 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.4 GB | 256k | 87tok/sest. | 3011 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.5 GB | 128k | 86tok/sest. | 3049 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.5 GB | 32k | 86tok/sest. | 2867 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 18.8 GB | 128k | 69tok/sest. | 3095 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 19.6 GB | 128k | 67tok/sest. | 3095 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.4 GB | 128k | 66tok/sest. | 1914 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 9.7 GB | 128k | 64tok/sest. | 1977 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.0 GB | 256k | 56tok/sest. | 1893 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.3 GB | 32k | 54tok/sest. | 1018 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.1 GB | 128k | 50tok/sest. | 1444 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 29.8 GB | 128k | 48tok/sest. | 2782 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 12.9 GB | 128k | 47tok/sest. | 975 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.5 GB | 64k | 41tok/sest. | 975 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.0 GB | 128k | 35tok/sest. | 1233 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.0 GB | 256k | 33tok/sest. | 1136 tok/s | chat, coding, agents, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 24.4 GB | 205k256k with q8 cache | 24tok/sest. | 830 tok/s | chat, coding, agents, long documents |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 24.5 GB | 256k | 24tok/sest. | 599 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 27.7 GB | 128k | 21tok/sest. | 664 tok/s | chat, coding |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 32.1 GB | 128k | 18tok/sest. | 604 tok/s | chat, long documents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 17tok/sest. | 597 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 34.4 GB | 40k | 17tok/sest. | 597 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 34.4 GB | 40k | 17tok/sest. | 597 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 17tok/sest. | 590 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 46.1 GB | 69k127k with q8 cache | 12tok/sest. | 441 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.8 GB | 48k78k with q8 cache | 81tok/sest. | 2872 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.6 GB | – | 29tok/sest. | 1361 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 61.8 GB | – | 19tok/sest. | 1659 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 54.8 GB | 24k44k with q8 cache | 8tok/sest. | 372 tok/s | chat, coding |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.8 GB | 49k79k with q8 cache | 94tok/sest. | 3277 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 60.7 GB | 22k41k with q8 cache | 3tok/sest. | 157 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | offload | 71.8 GB | – | 4tok/sest. | 317 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 60.7 GB | 22k41k with q8 cache | 3tok/sest. | 157 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.5 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 160.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 224.9 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 388.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.9 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- RTX 6000 Ada Generation
- Memory
- 48 GB GDDR6
- Memory bus
- 384-bit
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 91.1 TFLOPS
- Software
- CUDA
- Board power
- 300 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA RTX 6000 Ada Generation have for AI models?
- The NVIDIA RTX 6000 Ada Generation has 48 GB of GDDR6 memory with 960 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA RTX 6000 Ada Generation can run locally?
- Qwen 3.8 27B (Q8_0) fits fully in its memory at 64k context and generates at about 18 tok/s, an estimate from its memory bandwidth. 63 of the 125 models we track fit at that context.
- Can the NVIDIA RTX 6000 Ada Generation run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 97 GB at 64k context, more than the NVIDIA RTX 6000 Ada Generation and system RAM can hold.
- How much does the NVIDIA RTX 6000 Ada Generation cost in Germany?
- We have no current price for the NVIDIA RTX 6000 Ada Generation in Germany.
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.