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 64k context it runs 77 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 Flash Next at UD-Q3_K_XL, at about 9 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 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 Flash Next Alibaba Qwen | UD-Q3_K_XL | fits | 86.9 GB | 256k | 9tok/sest. | 131 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.7 GB | 256k | 14tok/sest. | 255 tok/s | chat |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 87.1 GB | 95k175k with q8 cache | 14tok/sest. | 242 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q5_K_M | fits | 88.3 GB | 256k | 32tok/sest. | 530 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 14tok/sest. | 255 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | fits | 62.8 GB | 128k | 52tok/sest. | 822 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 82.0 GB | 256k | 49tok/sest. | 1227 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q5_K_M | fits | 92.1 GB | 256k | 28tok/sest. | 616 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 37.7 GB | 256k | 12tok/sest. | 232 tok/s | – |
| Mistral Small 4 119B Mistral AI | Q6_K | fits | 93.8 GB | 98k156k with q8 cache | 39tok/sest. | 521 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 64tok/sest. | 1532 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 14tok/sest. | 255 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.9 GB | 256k | 50tok/sest. | 1569 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q5_K_M | fits | 90.8 GB | 85k128k with q8 cache | 13tok/sest. | 172 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 64tok/sest. | 1532 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 82.0 GB | 256k | 59tok/sest. | 1400 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.4 GB | 198k | 32tok/sest. | 760 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.8 GB | 384k | 13tok/sest. | 251 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.5 GB | 256k | 76tok/sest. | 1889 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.7 GB | 1024k | 76tok/sest. | 1231 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 128k | 71tok/sest. | 1173 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.7 GB | 256k | 30tok/sest. | 548 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 49.9 GB | 40k | 9tok/sest. | 130 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 256k | 34tok/sest. | 603 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 256k | 41tok/sest. | 738 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.6 GB | 128k | 14tok/sest. | 285 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 13tok/sest. | 251 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 49.9 GB | 128k | 9tok/sest. | 161 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 91.3 GB | 74k128k with q8 cache | 5tok/sest. | 77 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.8 GB | 256k | 19tok/sest. | 353 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.1 GB | 40k | 18tok/sest. | 309 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.6 GB | 128k | 26tok/sest. | 488 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.6 GB | 40k | 26tok/sest. | 488 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.5 GB | 16k | 16tok/sest. | 310 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 256k | 71tok/sest. | 1280 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.4 GB | 256k | 26tok/sest. | 483 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.2 GB | 128k | 24tok/sest. | 446 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 47tok/sest. | 967 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 125k | 67tok/sest. | 2063 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.6 GB | 128k | 31tok/sest. | 524 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.7 GB | 32k | 356tok/sest. | 4576 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.0 GB | 256k | 291tok/sest. | 5188 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.6 GB | 256k | 211tok/sest. | 2828 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.0 GB | 128k | 126tok/sest. | 1895 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.6 GB | 128k | 87tok/sest. | 1068 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.6 GB | 1024k | 86tok/sest. | 1312 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.4 GB | 128k | 78tok/sest. | 1912 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.8 GB | 256k | 70tok/sest. | 1280 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.9 GB | 128k | 69tok/sest. | 1295 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.9 GB | 32k | 69tok/sest. | 1218 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 19.2 GB | 128k | 56tok/sest. | 1315 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.0 GB | 128k | 54tok/sest. | 1315 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.8 GB | 128k | 53tok/sest. | 813 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 10.1 GB | 128k | 51tok/sest. | 840 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.4 GB | 256k | 45tok/sest. | 804 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.7 GB | 32k | 44tok/sest. | 433 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.5 GB | 128k | 40tok/sest. | 614 tok/s | chat, coding, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 30.2 GB | 128k | 38tok/sest. | 1182 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.3 GB | 128k | 38tok/sest. | 414 tok/s | chat, coding, agents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.9 GB | 64k | 33tok/sest. | 414 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.4 GB | 128k | 28tok/sest. | 524 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.4 GB | 256k | 26tok/sest. | 483 tok/s | chat, coding, agents, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 24.8 GB | 256k | 19tok/sest. | 353 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 24.9 GB | 256k | 19tok/sest. | 255 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 28.1 GB | 128k | 17tok/sest. | 282 tok/s | chat, coding |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 32.5 GB | 128k | 14tok/sest. | 257 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | fits | 72.2 GB | 64k | 14tok/sest. | 170 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 13tok/sest. | 254 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 34.8 GB | 40k | 13tok/sest. | 254 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 34.8 GB | 40k | 13tok/sest. | 254 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 34.8 GB | 128k | 13tok/sest. | 251 tok/s | chat |
| GLM 4.6V Z.ai | Q4_K_M | fits | 78.6 GB | 128k | 13tok/sest. | 170 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 46.5 GB | 128k | 10tok/sest. | 188 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 91.3 GB | 74k128k with q8 cache | 5tok/sest. | 77 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | fits | 93.2 GB | 68k127k with q8 cache | 5tok/sest. | 45 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q8_0 | fits | 93.4 GB | 68k126k with q8 cache | 5tok/sest. | 75 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | fits | 93.2 GB | 68k127k with q8 cache | 5tok/sest. | 44 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | offload | 97.0 GB | 39k69k with q8 cache | 19tok/sest. | 76 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | offload | 103.5 GB | – | 18tok/sest. | 112 tok/s | chat |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.3 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 225.3 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 389.3 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.9 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.8 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.3 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.2 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.7 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 Flash Next (UD-Q3_K_XL) fits fully in its memory at 64k context and generates at about 9 tok/s, an estimate from its memory bandwidth. 77 of the 125 models we track fit at that context.
- Can the NVIDIA RTX A6000 run DeepSeek V4 Flash?
- Not fully in memory: at UD-Q2_K_XL and 64k context DeepSeek V4 Flash needs about 97 GB, so part of it runs from system RAM and it slows to about 19 tok/s (estimated).
- 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 64k context. See the best hardware for local AI at every budget.