Phi-4 Mini Reasoning 4B needs ~9.5 GB VRAM. NVIDIA L40 48GB has 48.0 GB. With Q4_K_M quantization, expect ~61 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
60.8 tok/s
TTFT
3184 ms
Safe context
131K
Memory
9.5 GB / 48.0 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 | 60.8 tok/s | 1737 ms | 131K |
| Coding | A | Runs well | 60.8 tok/s | 3184 ms | 131K |
| Agentic Coding | A | Runs well | 60.8 tok/s | 4632 ms | 131K |
| Reasoning | A | Runs well | 60.8 tok/s | 3763 ms | 131K |
| RAG | A | Runs well | 60.8 tok/s | 5789 ms | 131K |
How Phi-4 Mini Reasoning 4B (3.799999952316284B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.5 GB | Low | A78 |
Q3_K_S | 3 | 1.9 GB | Low | A78 |
NVFP4 | 4 | 2.1 GB | Medium | A78 |
Q4_K_M | 4 | 2.3 GB | Medium | A78 |
Q5_K_M | 5 | 2.7 GB | High | A78 |
Q6_K | 6 | 3.1 GB | High | A78 |
Q8_0 | 8 | 4.1 GB | Very High | A79 |
F16Best for your GPU | 16 | 7.8 GB | Maximum | A79 |
Copy-paste commands to run Phi-4 Mini Reasoning 4B on your machine.
Run
ollama run phi4-miniYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 73.4 tok/s | |
| Qwen 3.5 27B | 27B | S | 30.6 tok/s | |
| Qwen 3.6 27B | 27B | S | 20.1 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 91.6 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 105.4 tok/s |
Yes, NVIDIA L40 48GB can run Phi-4 Mini Reasoning 4B with a A grade (Runs well). Expected decode speed: 60.8 tok/s.
Phi-4 Mini Reasoning 4B (3.799999952316284B parameters) requires approximately 9.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi-4 Mini Reasoning 4B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA L40 48GB, Phi-4 Mini Reasoning 4B achieves approximately 60.8 tokens per second decode speed with a time-to-first-token of 3184ms using Q4_K_M quantization.
For coding workloads, Phi-4 Mini Reasoning 4B on NVIDIA L40 48GB receives a A grade with 60.8 tok/s and 131K context.
On NVIDIA L40 48GB, 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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-4-mini-reasoning-on-l40-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: