RTX 6000 Ada Generation
48 GB GDDR6 ECC · 960 GB/s · 300 W
RTX 6000 Ada 48 GB · 64 GB RAM → Llama 3.3 70B Instruct
GPU · NVIDIA
RTX 6000 Ada for local LLMs: which models run?
With 48 GB of VRAM and 960 GB/s of bandwidth, the RTX 6000 Ada runs models up to about Llama 3.3 70B Instruct entirely on the GPU.
- VRAM48 GB GDDR6 ECC
- Bandwidth960 GB/s
- Board power300 W
- ArchitectureAda Lovelace
Specifications
- VRAM
- 48 GB
- Memory type
- GDDR6 ECC
- Memory bus
- 384-bit
- Bandwidth
- 960 GB/s
- Board power
- 300 W
- Backends
- CUDA, Vulkan
- Interface
- PCIe 4.0 x16
- Released
- December 2022
- Segment
- Workstation
- FP16 compute
- Not available
Official specData updated 24 days agoSource: NVIDIA specifications
What the RTX 6000 Ada runs
| Mixtral 8x7B InstructQ6_K · 8K~39.2 GB · 48–66 tok/s estimate | Excellent |
|---|---|
| Qwen3 32BQ8_0 · 8K~37 GB · 19–26 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 32BQ8_0 · 8K~37 GB · 19–26 tok/s estimate | Excellent |
| Qwen2.5 32B InstructQ8_0 · 8K~37 GB · 19–26 tok/s estimate | Excellent |
| Qwen2.5 Coder 32B InstructQ8_0 · 8K~37 GB · 19–26 tok/s estimate | Excellent |
| QwQ 32BQ8_0 · 8K~37 GB · 19–26 tok/s estimate | Excellent |
| Qwen3 30B-A3BQ8_0 · 8K~33.4 GB · 94–147 tok/s estimate | Excellent |
| Qwen3 Coder 30B-A3B InstructQ8_0 · 8K~33.4 GB · 85–236 tok/s estimate | Excellent |
| Gemma 3 27B ITQ8_0 · 8K~30.2 GB · 23–31 tok/s estimate | Excellent |
| Gemma 2 27B ITQ8_0 · 8K~31.6 GB · 23–31 tok/s estimate | Excellent |
| Mistral Small 3.2 24B InstructQ8_0 · 8K~26.6 GB · 27–36 tok/s estimate | Excellent |
| gpt-oss-20bMXFP4 · 8K~13 GB · 121–334 tok/s estimate | Excellent |
| Qwen3 14BQ8_0 · 8K~17.5 GB · 41–55 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 14BQ8_0 · 8K~17.8 GB · 40–54 tok/s estimate | Excellent |
| Qwen2.5 14B InstructQ8_0 · 8K~17.8 GB · 40–54 tok/s estimate | Excellent |
| Phi-4 14BQ8_0 · 8K~17.6 GB · 41–55 tok/s estimate | Excellent |
| Mistral Nemo 12B InstructQ8_0 · 8K~14.9 GB · 48–66 tok/s estimate | Excellent |
| Gemma 3 12B ITQ8_0 · 8K~14.1 GB · 49–68 tok/s estimate | Excellent |
| Gemma 2 9B ITQ8_0 · 8K~12.7 GB · 58–81 tok/s estimate | Excellent |
| Qwen3 8BQ8_0 · 8K~10.5 GB · 68–95 tok/s estimate | Excellent |
| Llama 3.1 8B InstructQ8_0 · 8K~10.2 GB · 71–98 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8BQ8_0 · 8K~10.2 GB · 71–98 tok/s estimate | Excellent |
| Qwen2.5 7B InstructQ8_0 · 8K~9.2 GB · 77–107 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3Q8_0 · 8K~9.2 GB · 77–107 tok/s estimate | Excellent |
| Gemma 3 4B ITQ8_0 · 8K~5.4 GB · 128–192 tok/s estimate | Excellent |
| Qwen3 4BQ8_0 · 8K~6.2 GB · 114–170 tok/s estimate | Excellent |
| Phi-4 Mini Instruct 3.8BQ8_0 · 8K~6 GB · 123–181 tok/s estimate | Excellent |
| Llama 3.2 3B InstructQ8_0 · 8K~5.1 GB · 144–214 tok/s estimate | Excellent |
| Qwen3 1.7BQ8_0 · 8K~3.7 GB · 209–334 tok/s estimate | Excellent |
| Llama 3.2 1B InstructQ8_0 · 8K~2.5 GB · 342–539 tok/s estimate | Excellent |
| Qwen3 0.6BQ8_0 · 8K~2.5 GB · 315–578 tok/s estimate | Excellent |
| Qwen2.5 72B InstructIQ4_XS · 8K~42.4 GB · 17–22 tok/s estimate | Compatible |
| Llama 3.3 70B InstructQ4_K_M · 8K~45.1 GB · 16–21 tok/s estimate | Compatible |
| DeepSeek R1 Distill Llama 70BQ4_K_M · 8K~45.1 GB · 16–21 tok/s estimate | Compatible |
| gpt-oss-120bMXFP4 · 8K~63.2 GB · 21–41 tok/s estimate | CPU/GPU offload |
| Llama 4 Scout 17B-16E InstructQ3_K_M · 8K~55.7 GB · 10–20 tok/s estimate | CPU/GPU offload |
| DeepSeek R1 (671B)Q8_0 · 8K~699 GB · No data | Incompatible |
| Qwen3 235B-A22BQ8_0 · 8K~247 GB · No data | Incompatible |
For each model, the highest-precision quantization that runs entirely in fast memory; otherwise the one with the best result. Speeds are ranges; "estimate" unless a benchmark exists for this exact hardware.
EstimateData updated 24 days agoSource: Run LLM Locally engine
Limits in plain words
48 GB of VRAM holds the weights and KV cache of models up to about Llama 3.3 70B Instruct at Q4_K_M. Bigger models spill into system RAM and slow down sharply: generation speed is then limited by RAM bandwidth, not by the GPU.
Where to buy a RTX 6000 Ada
Prices and links follow the market you choose.
No current offer imported for this market: the link opens a marketplace search.
Frequently asked questions
Which LLMs can the RTX 6000 Ada run?
Entirely on the GPU: Qwen2.5 72B Instruct (IQ4_XS), Llama 3.3 70B Instruct (Q4_K_M), DeepSeek R1 Distill Llama 70B (Q4_K_M), Mixtral 8x7B Instruct (Q6_K), Qwen3 32B (Q8_0), DeepSeek R1 Distill Qwen 32B (Q8_0), Qwen2.5 32B Instruct (Q8_0), Qwen2.5 Coder 32B Instruct (Q8_0). Larger models need CPU/GPU offload.
Can the RTX 6000 Ada run a 70B model?
Compatible: a 70B model at Q4_K_M needs about 45.1 GB; the RTX 6000 Ada has 48 GB.
How is the speed estimated?
Token generation reads every active weight once per token, so it is limited by memory bandwidth (960 GB/s here). We apply an efficiency range per backend and label the result as an estimate until real benchmarks exist.