Can Phi-4 Mini Reasoning 4B run on RTX PRO 6000 Blackwell Workstation Edition 96GB?
YES — Runs Great
A80Great○Estimated from fit model
Phi-4 Mini Reasoning 4B needs ~14.6 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~53 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced
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
Q4_K_M (Medium quality) — 14.6 GB, 53.2 tok/s, Runs well
14.6 GB required96.0 GB available
Memory breakdown
Weights2.3 GB
KV Cache1.5 GB
Runtime1.2 GB
Headroom9.6 GB
See how fast it feels
See how fast it feelsPhi-4 Mini Reasoning 4B on RTX PRO 6000 Blackwell Workstation Edition 96GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 53.2 tok/s decode · 3.6s TTFT (warm) · 133 tok/s prefill
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 | Runs well | 53.2 tok/s | 1985 ms | 131K |
| Coding | A | Runs well | 53.2 tok/s | 3639 ms | 131K |
| Agentic Coding | A | Runs well | 53.2 tok/s | 5293 ms | 131K |
| Reasoning | A | Runs well | 53.2 tok/s | 4301 ms | 131K |
| RAG | A | Runs well | 53.2 tok/s | 6617 ms | 131K |
Quantization options
How Phi-4 Mini Reasoning 4B (3.799999952316284B 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 | 1.5 GB | Low | A76 |
Q3_K_S | 3 | 1.9 GB | Low | A76 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Phi-4 Mini Reasoning 4B on your machine.
Your hardware
More models your RTX PRO 6000 Blackwell Workstation Edition 96GB can run
| Model | Params | Grade | Decode | Capabilities |
|---|
👁 Mistral
Devstral 2 123B Instruct | 123B | S | 21.8 tok/s |
👁 Alibaba
Qwen3-Coder 30B A3B Instruct | 30.5B |
Frequently asked questions
F16Best for your GPU | 16 | 7.8 GB | Maximum | A76 |
S
On RTX PRO 6000 Blackwell Workstation Edition 96GB, Phi-4 Mini Reasoning 4B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
