NVIDIA RTX A6000
48 GB · 768 GB/s · 300 W
In short
The NVIDIA RTX A6000 has 48 GB of GDDR6 memory with 768 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 68 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 16 tok/s (estimated). We have no current price for the NVIDIA RTX A6000 in the US.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, 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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 16tok/sest. | 305 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.0 GB | 256k | 77tok/sest. | 806 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 16tok/sest. | 305 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.2 GB | 48k78k with q8 cache | 108tok/sest. | 2036 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 32.5 GB | 184k256k with q8 cache | 14tok/sest. | 266 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.4 GB | 332k528k with q8 cache | 111tok/sest. | 1053 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 86tok/sest. | 2611 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 16tok/sest. | 305 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.1 GB | 256k | 63tok/sest. | 1990 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 44.4 GB | 24k44k with q8 cache | 39tok/sest. | 480 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.2 GB | 49k79k with q8 cache | 138tok/sest. | 2560 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 86tok/sest. | 2611 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.8 GB | 198k | 50tok/sest. | 1461 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 144k262k with q8 cache | 18tok/sest. | 344 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.4 GB | 256k | 83tok/sest. | 2721 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.5 GB | 662k902k with q8 cache | 111tok/sest. | 2482 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 109tok/sest. | 1890 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 31.7 GB | 165k256k with q8 cache | 72tok/sest. | 1889 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 40k | 13tok/sest. | 235 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 36tok/sest. | 693 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 48tok/sest. | 878 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 18tok/sest. | 344 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 28.5 GB | 128k | 16tok/sest. | 309 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.2 GB | 55k102k with q8 cache | 13tok/sest. | 246 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | fits | 42.8 GB | 22k41k with q8 cache | 11tok/sest. | 115 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 205k256k with q8 cache | 30tok/sest. | 570 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 28tok/sest. | 530 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 128k | 48tok/sest. | 927 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 48tok/sest. | 927 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 28tok/sest. | 533 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 99tok/sest. | 1767 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 47tok/sest. | 866 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 128k | 45tok/sest. | 860 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 56tok/sest. | 1064 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 195tok/sest. | 6210 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 128k | 62tok/sest. | 957 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 754tok/sest. | 12996 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 511tok/sest. | 8941 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 306tok/sest. | 3668 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 224tok/sest. | 4090 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 157tok/sest. | 2704 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 141tok/sest. | 2721 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 141tok/sest. | 2402 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 3.9 GB | 1024k | 140tok/sest. | 1924 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 111tok/sest. | 1801 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.0 GB | 256k | 105tok/sest. | 1845 tok/s | chat, coding, agents, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 104tok/sest. | 1936 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.1 GB | 128k | 102tok/sest. | 3261 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 101tok/sest. | 2992 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.3 GB | 256k | 96tok/sest. | 1767 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 16.8 GB | 128k | 85tok/sest. | 2522 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 81tok/sest. | 2522 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 56tok/sest. | 1032 tok/s | chat, coding, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 8.7 GB | 32k | 56tok/sest. | 811 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 128k | 50tok/sest. | 957 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 47tok/sest. | 866 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 46tok/sest. | 749 tok/s | chat, coding, agents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 39tok/sest. | 749 tok/s | chat, coding |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.4 GB | 205k256k with q8 cache | 30tok/sest. | 570 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 128k | 28tok/sest. | 519 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 20.6 GB | 256k | 22tok/sest. | 305 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 18tok/sest. | 350 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 18tok/sest. | 350 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 18tok/sest. | 350 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 18tok/sest. | 344 tok/s | chat |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.0 GB | 128k | 15tok/sest. | 282 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 31.7 GB | 69k127k with q8 cache | 14tok/sest. | 277 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | fits | 42.8 GB | 22k41k with q8 cache | 11tok/sest. | 115 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 72.8 GB | – | 13tok/sest. | 485 tok/s | – |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 59.5 GB | – | 32tok/sest. | 1198 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 51.9 GB | – | 31tok/sest. | 673 tok/s | chat, coding, long documents |
| GLM 4.5V Z.ai | Q4_K_M | offload | 61.4 GB | – | 10tok/sest. | 397 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 67.8 GB | – | 8tok/sest. | 377 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q6_K | offload | 63.2 GB | – | 2tok/sest. | 95 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | offload | 73.3 GB | – | 2tok/sest. | 51 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | offload | 73.3 GB | – | 2tok/sest. | 50 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.5 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.4 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.4 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 383.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.0 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.4 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- RTX A6000
- Memory
- 48 GB GDDR6
- Memory bus
- 384-bit
- Memory bandwidth
- 768 GB/s
- FP16 compute
- 38.71 TFLOPS
- Software
- CUDA
- Board power
- 300 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA RTX A6000 have for AI models?
- The NVIDIA RTX A6000 has 48 GB of GDDR6 memory with 768 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA RTX A6000 can run locally?
- Qwen 3.8 27B (Q8_0) fits fully in its memory at 8k context and generates at about 16 tok/s, an estimate from its memory bandwidth. 68 of the 125 models we track fit at that context.
- Can the NVIDIA RTX A6000 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 92 GB at 8k context, more than the NVIDIA RTX A6000 and system RAM can hold.
- How much does the NVIDIA RTX A6000 cost in the US?
- We have no current price for the NVIDIA RTX A6000 in the US.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.