NVIDIA RTX A6000
The NVIDIA RTX A6000 has 48 GB VRAM and 768 GB/s memory bandwidth. It can run 52 of our 70 tracked models natively in VRAM at 8k context.
With 48 GB GDDR6, the NVIDIA RTX A6000 is a workstation-tier GPU that can run 52 models natively. It handles 70B-class models at Q4 quantization.
The NVIDIA RTX A6000 is an Ampere-generation workstation GPU with 48GB of ECC GDDR6 VRAM. Released in 2020, it bridges consumer RTX cards and data center A100s — running full CUDA drivers, supporting NVLink for multi-GPU setups, and fitting inside standard workstation towers. Its 48GB capacity lets it run 34B models at Q4 and most 70B models with CPU offload, making it a long-running workhorse for on-prem AI labs.
NVIDIA RTX A6000: 2020 Ampere workstation with 48GB GDDR6 at 768 GB/s. Bridges consumer and datacenter.
70B at Q4 native. ~25-35 t/s for 7B, ~10-15 t/s for 70B.
Full CUDA with ECC memory. NVLink support for multi-GPU. Long-running workhorse for on-prem AI labs.
| Vendor | NVIDIA |
| Architecture | Ampere |
| VRAM | 48 GB |
| Memory type | GDDR6 |
| Memory bandwidth | 768 GB/s |
| Compute backend | CUDA |
| Tier | Workstation |
| Released | 2020 |
| Models (native) | 52 / 70 |
| Models (offload) | 2 / 70 |
Software: Full llama.cpp and Ollama support out of the box. CUDA 12.x recommended; driver ≥ 525 required.
Popular models for this GPU
Models this GPU runs natively in VRAM (52)
- Nemotron 3 Super 120B120B · MMLU-Pro 83.7Q2_K · ~214 t/s
- GPT-OSS 120B117B · MMLU-Pro 80.7Q2_K · ~513.6 t/s
- Llama 4 Scout 109B109B · MMLU-Pro 74.3Q2_K · ~151 t/s
- GLM-4.5 Air 106B106B · MMLU-Pro 81.4Q2_K · ~214 t/s
- GLM-4.6V 106B106B · MMLU-Pro 79.9Q2_K · ~214 t/s
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1NVFP4 · ~21.3 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9NVFP4 · ~21.9 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0NVFP4 · ~21.9 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4NVFP4 · ~21.9 t/s
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7NVFP4 · ~131 t/s
- Command-R 35B35B · MMLU-Pro 33.0NVFP4 · ~43.9 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 84.2NVFP4 · ~563.2 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2NVFP4 · ~43.9 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0NVFP4 · ~44.7 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5NVFP4 · ~46.8 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0NVFP4 · ~47.3 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4NVFP4 · ~47.3 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0NVFP4 · ~47.3 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3NVFP4 · ~563.2 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2NVFP4 · ~49.5 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5NVFP4 · ~563.2 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0NVFP4 · ~56.5 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5NVFP4 · ~56.9 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2NVFP4 · ~56.9 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6NVFP4 · ~444.6 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8NVFP4 · ~64 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2NVFP4 · ~69.2 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9NVFP4 · ~422.4 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0BF16 · ~25.9 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7BF16 · ~26.1 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4BF16 · ~27.4 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6BF16 · ~31.5 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6BF16 · ~31.5 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0FP32 · ~20.9 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3FP32 · ~24 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0FP32 · ~24 t/s
- Qwen3 8B8B · MMLU-Pro 56.7FP32 · ~24 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3FP32 · ~25.3 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0FP32 · ~26.5 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~48 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~48 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~50.5 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~60 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~61.9 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~73.8 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~96 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~112.9 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~128 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~154.8 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~192 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~384 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~533.3 t/s
Models that fit with CPU offload (2)
These use system RAM for layers that don't fit in VRAM — expect much slower inference.
Too large for this GPU (16)
Compare NVIDIA RTX A6000 with other GPUs
Frequently asked questions
- How much VRAM does the NVIDIA RTX A6000 have?
- The NVIDIA RTX A6000 has 48 GB of GDDR6 with 768 GB/s memory bandwidth.
- What is the NVIDIA RTX A6000 best for?
- With 48 GB of VRAM, the NVIDIA RTX A6000 is ideal for running 70B-class models at Q4 quantization and large MoE models — a workstation sweet spot for local inference.
- What LLMs can the NVIDIA RTX A6000 run locally?
- The NVIDIA RTX A6000 can run 52 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at NVFP4, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
- Can the NVIDIA RTX A6000 run Llama 3.3 70B Instruct?
- Yes. The NVIDIA RTX A6000 runs Llama 3.3 70B Instruct natively in VRAM at NVFP4 quantization, achieving approximately 21.9 tokens per second.
- Can the NVIDIA RTX A6000 run Qwen 3.6 27B?
- Yes. The NVIDIA RTX A6000 runs Qwen 3.6 27B natively in VRAM at NVFP4 quantization, achieving approximately 56.9 tokens per second.
- Can the NVIDIA RTX A6000 run Llama 3.1 8B Instruct?
- Yes. The NVIDIA RTX A6000 runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 24 tokens per second.