Phi-4-reasoning-plus 14B needs ~47.4 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~8 tok/s.
Operating mode
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
Runs well
Decode
19.6 tok/s
TTFT
9859 ms
Safe context
33K
Memory
26.3 GB / 108.8 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 3.3 tok/s | 32116 ms | 4K |
| Coding | F | Too heavy | 3.3 tok/s | 58880 ms | 4K |
| Agentic Coding | F | Too heavy | 3.3 tok/s | 85643 ms | 4K |
| Reasoning | F | Too heavy | 3.3 tok/s | 69585 ms | 4K |
| RAG | F | Too heavy | 3.3 tok/s | 107054 ms | 4K |
How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.7 GB | Low | A79 |
Q3_K_S | 3 | 7.2 GB | Low | A79 |
NVFP4 | 4 | 8.2 GB | Medium | A79 |
Q4_K_M | 4 | 9.0 GB | Medium | A79 |
Q5_K_M | 5 | 10.6 GB | High | A79 |
Q6_K | 6 | 12.1 GB | High | A79 |
Q8_0 | 8 | 15.7 GB | Very High | A80 |
F16Best for your GPU | 16 | 30.1 GB | Maximum | A82 |
Copy-paste commands to run Phi-4-reasoning-plus 14B on your machine.
Run
ollama run phi4-reasoningアップグレードオプション
NVIDIA H200 141GBコスパ重視Raises estimated decode speed by about 950%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
NVIDIA H200 PCIe 141GBコスパ最良Raises estimated decode speed by about 950%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
NVIDIA B200 180GBNVIDIAアップグレードRaises estimated decode speed by about 950%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Phi-4-reasoning-plus 14B at F16 quantization (Runs well). The recommended Q4_K_M requires 13.2 GB which exceeds available memory, but at F16 it needs only 47.4 GB. Expected decode speed: 8.2 tok/s.
Phi-4-reasoning-plus 14B (14.699999809265137B parameters) requires approximately 13.2 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 47.4 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 47.4 GB.
On NVIDIA DGX Spark 128GB, Phi-4-reasoning-plus 14B achieves approximately 8.2 tokens per second decode speed with a time-to-first-token of 23666ms using F16 quantization.
For coding workloads, Phi-4-reasoning-plus 14B on NVIDIA DGX Spark 128GB receives a F grade with 3.3 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, Phi-4-reasoning-plus 14B can safely use up to 33K tokens of context at F16 quantization. The model's official context limit is 33K, but available memory constrains the safe maximum.
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-4-reasoning-plus-14b-on-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: