Phi 3 Medium 14B needs ~25.8 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~21 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
20.6 tok/s
TTFT
9389 ms
Safe context
128K
Memory
25.8 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 | C | Runs well | 20.6 tok/s | 5122 ms | 128K |
| Coding | C | Runs well | 20.6 tok/s | 9389 ms | 128K |
| Agentic Coding | C | Runs well | 20.6 tok/s | 13657 ms | 128K |
| Reasoning | C | Runs well | 20.6 tok/s | 11097 ms | 128K |
| RAG | C | Runs well | 20.6 tok/s | 17072 ms | 128K |
How Phi 3 Medium 14B (14B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C50 |
Q3_K_S | 3 | 6.9 GB | Low | C50 |
NVFP4 | 4 | 7.8 GB | Medium | C50 |
Q4_K_M | 4 | 8.5 GB | Medium | C50 |
Q5_K_M | 5 | 10.1 GB | High | C51 |
Q6_K | 6 | 11.5 GB | High | C51 |
Q8_0 | 8 | 15.0 GB | Very High | C51 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | C53 |
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumOpciones de mejora
NVIDIA H200 141GBOpción económicaSube la velocidad estimada de decodificación alrededor de un 851%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$30,000 MSRP
NVIDIA H200 PCIe 141GBMejor relación calidad-precioSube la velocidad estimada de decodificación alrededor de un 851%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$30,000 MSRP
NVIDIA B200 180GBMejora NVIDIASube la velocidad estimada de decodificación alrededor de un 851%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Phi 3 Medium 14B with a C grade (Runs well). Expected decode speed: 20.6 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 25.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA DGX Spark 128GB, Phi 3 Medium 14B achieves approximately 20.6 tokens per second decode speed with a time-to-first-token of 9389ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on NVIDIA DGX Spark 128GB receives a C grade with 20.6 tok/s and 128K context.
On NVIDIA DGX Spark 128GB, Phi 3 Medium 14B can safely use up to 128K tokens of context. The model's official context limit is 128K, 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-3-medium-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: