RTX PRO 6000 Blackwell Workstation Edition
96 GB GDDR7 ECC · 1,792 GB/s · 600 W
RTX PRO 6000 Blackwell 96 GB · 64 GB RAM → gpt-oss-120b
GPU · NVIDIA
RTX PRO 6000 Blackwell for local LLMs: which models run?
With 96 GB of VRAM and 1792 GB/s of bandwidth, the RTX PRO 6000 Blackwell runs models up to about gpt-oss-120b entirely on the GPU.
- VRAM96 GB GDDR7 ECC
- Bandwidth1,792 GB/s
- Board power600 W
- ArchitectureBlackwell
Specifications
- VRAM
- 96 GB
- Memory type
- GDDR7 ECC
- Memory bus
- 512-bit
- Bandwidth
- 1,792 GB/s
- Board power
- 600 W
- Backends
- CUDA, Vulkan
- Interface
- PCIe 5.0 x16
- Released
- April 2025
- Segment
- Workstation
- FP16 compute
- Not available
Official specData updated 24 days agoSource: NVIDIA specifications
What the RTX PRO 6000 Blackwell runs
| gpt-oss-120bMXFP4 · 8K~63.2 GB · 168–205 tok/s measured | Excellent |
|---|---|
| Llama 3.3 70B InstructQ8_0 · 8K~76.8 GB · 17–22 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 70BQ8_0 · 8K~76.8 GB · 17–22 tok/s estimate | Excellent |
| Mixtral 8x7B InstructQ8_0 · 8K~50.2 GB · 66–93 tok/s estimate | Excellent |
| Qwen3 32BQ8_0 · 8K~37 GB · 34–46 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 32BQ8_0 · 8K~37 GB · 34–46 tok/s estimate | Excellent |
| Qwen2.5 32B InstructQ8_0 · 8K~37 GB · 34–46 tok/s estimate | Excellent |
| Qwen2.5 Coder 32B InstructQ8_0 · 8K~37 GB · 34–46 tok/s estimate | Excellent |
| QwQ 32BQ8_0 · 8K~37 GB · 34–46 tok/s estimate | Excellent |
| Qwen3 30B-A3BQ8_0 · 8K~33.4 GB · 130–221 tok/s estimate | Excellent |
| Qwen3 Coder 30B-A3B InstructQ8_0 · 8K~33.4 GB · 159–441 tok/s estimate | Excellent |
| Gemma 3 27B ITQ8_0 · 8K~30.2 GB · 40–56 tok/s estimate | Excellent |
| Gemma 2 27B ITQ8_0 · 8K~31.6 GB · 41–56 tok/s estimate | Excellent |
| Mistral Small 3.2 24B InstructQ8_0 · 8K~26.6 GB · 48–65 tok/s estimate | Excellent |
| gpt-oss-20bMXFP4 · 8K~13 GB · 247–301 tok/s measured | Excellent |
| Qwen3 14BQ8_0 · 8K~17.5 GB · 70–100 tok/s estimate | Excellent |
| DeepSeek R1 Distill Qwen 14BQ8_0 · 8K~17.8 GB · 68–97 tok/s estimate | Excellent |
| Qwen2.5 14B InstructQ8_0 · 8K~17.8 GB · 68–97 tok/s estimate | Excellent |
| Phi-4 14BQ8_0 · 8K~17.6 GB · 70–99 tok/s estimate | Excellent |
| Mistral Nemo 12B InstructQ8_0 · 8K~14.9 GB · 81–117 tok/s estimate | Excellent |
| Gemma 3 12B ITQ8_0 · 8K~14.1 GB · 82–121 tok/s estimate | Excellent |
| Gemma 2 9B ITQ8_0 · 8K~12.7 GB · 96–143 tok/s estimate | Excellent |
| Qwen3 8BQ8_0 · 8K~10.5 GB · 113–167 tok/s estimate | Excellent |
| Llama 3.1 8B InstructQ8_0 · 8K~10.2 GB · 118–173 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8BQ8_0 · 8K~10.2 GB · 118–173 tok/s estimate | Excellent |
| Qwen2.5 7B InstructQ8_0 · 8K~9.2 GB · 130–190 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3Q8_0 · 8K~9.2 GB · 127–189 tok/s estimate | Excellent |
| Gemma 3 4B ITQ8_0 · 8K~5.4 GB · 195–322 tok/s estimate | Excellent |
| Qwen3 4BQ8_0 · 8K~6.2 GB · 176–287 tok/s estimate | Excellent |
| Phi-4 Mini Instruct 3.8BQ8_0 · 8K~6 GB · 190–308 tok/s estimate | Excellent |
| Llama 3.2 3B InstructQ8_0 · 8K~5.1 GB · 223–363 tok/s estimate | Excellent |
| Qwen3 1.7BQ8_0 · 8K~3.7 GB · 299–537 tok/s estimate | Excellent |
| Llama 3.2 1B InstructQ8_0 · 8K~2.5 GB · 497–876 tok/s estimate | Excellent |
| Qwen3 0.6BQ8_0 · 8K~2.5 GB · 403–843 tok/s estimate | Excellent |
| Llama 4 Scout 17B-16E InstructQ6_K · 8K~89 GB · 59–86 tok/s estimate | Compatible |
| Qwen2.5 72B InstructQ8_0 · 8K~79.3 GB · 16–22 tok/s estimate | Compatible |
| Qwen3 235B-A22BQ3_K_M · 8K~112 GB · 8.5–17 tok/s estimate | CPU/GPU offload |
| DeepSeek R1 (671B)Q8_0 · 8K~699 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
96 GB of VRAM holds the weights and KV cache of models up to about gpt-oss-120b 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 PRO 6000 Blackwell
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 PRO 6000 Blackwell run?
Entirely on the GPU: gpt-oss-120b (MXFP4), Llama 4 Scout 17B-16E Instruct (Q6_K), Qwen2.5 72B Instruct (Q8_0), Llama 3.3 70B Instruct (Q8_0), DeepSeek R1 Distill Llama 70B (Q8_0), Mixtral 8x7B Instruct (Q8_0), Qwen3 32B (Q8_0), DeepSeek R1 Distill Qwen 32B (Q8_0). Larger models need CPU/GPU offload.
Can the RTX PRO 6000 Blackwell run a 70B model?
Excellent: a 70B model at Q4_K_M needs about 45.1 GB; the RTX PRO 6000 Blackwell has 96 GB.
How is the speed estimated?
Token generation reads every active weight once per token, so it is limited by memory bandwidth (1792 GB/s here). We apply an efficiency range per backend and label the result as an estimate until real benchmarks exist.