Phi-4 14B needs ~20.8 GB VRAM. NVIDIA A800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~190 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
190.0 tok/s
TTFT
1019 ms
Safe context
16K
Memory
20.8 GB / 80.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 190.0 tok/s | 556 ms | 16K |
| Coding | A | Runs well | 190.0 tok/s | 1019 ms | 16K |
| Agentic Coding | A | Runs well | 190.0 tok/s | 1482 ms | 16K |
| Reasoning | A | Runs well | 190.0 tok/s | 1204 ms | 16K |
| RAG | A | Runs well | 190.0 tok/s | 1853 ms | 16K |
How Phi-4 14B (14B params) fits at each quantization level on NVIDIA A800 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A71 |
Q3_K_S | 3 | 6.9 GB | Low | A72 |
NVFP4 | 4 | 7.8 GB | Medium | A72 |
Q4_K_M | 4 | 8.5 GB | Medium | A72 |
Q5_K_M | 5 | 10.1 GB | High | A72 |
Q6_K | 6 | 11.5 GB | High | A72 |
Q8_0 | 8 | 15.0 GB | Very High | A72 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | A75 |
Copy-paste commands to run Phi-4 14B on your machine.
Run
ollama run phi4Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | A | 15.5 tok/s | |
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 228.2 tok/s | |
| Qwen 3.5 27B | 27B | S | 99 tok/s | |
| Qwen 3.6 27B | 27B | S | 99.3 tok/s | |
| Qwen 3.5 122B A10B | 122B | A | 45.9 tok/s |
Yes, NVIDIA A800 80GB can run Phi-4 14B with a A grade (Runs well). Expected decode speed: 190.0 tok/s.
Phi-4 14B (14B parameters) requires approximately 20.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi-4 14B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA A800 80GB, Phi-4 14B achieves approximately 190.0 tokens per second decode speed with a time-to-first-token of 1019ms using Q4_K_M quantization.
For coding workloads, Phi-4 14B on NVIDIA A800 80GB receives a A grade with 190.0 tok/s and 16K context.
On NVIDIA A800 80GB, Phi-4 14B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-4-14b-on-a800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: