Can Llama 4 Scout 17B 16E run on RTX PRO 6000 Blackwell Workstation Edition 96GB?
YES — Tight Fit
Llama 4 Scout 17B 16E needs ~80.2 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~58 tok/s.
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Tight fit
Decode
57.6 tok/s
TTFT
3363 ms
Safe context
102K
Memory
80.2 GB / 96.0 GB
Memory breakdown
See how fast it feels
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Tight fit | 57.6 tok/s | 1835 ms | 102K |
| Coding | A | Tight fit | 57.6 tok/s | 3363 ms | 102K |
| Agentic Coding | A | Tight fit | 57.6 tok/s | 4892 ms | 102K |
| Reasoning | A | Tight fit | 57.6 tok/s | 3975 ms | 102K |
| RAG | A | Tight fit | 57.6 tok/s | 6115 ms | 102K |
Quantization options
How Llama 4 Scout 17B 16E (109B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 42.5 GB | Low | A74 |
Q3_K_S | 3 | 53.4 GB | Low | A76 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Llama 4 Scout 17B 16E on your machine.
Run
lms load Llama-4-Scout-17B-16E-Instruct && lms server startYour hardware
