Phi 4 Mini 4B needs ~5.4 GB VRAM. Intel Arc A380 6GB has 6.0 GB. With Q4_K_M quantization, expect ~40 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
Tight fit
Decode
40.2 tok/s
TTFT
4821 ms
Safe context
23K
Memory
5.4 GB / 6.0 GB
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 40.2 tok/s | 2630 ms | 23K |
| Coding | A | Tight fit | 40.2 tok/s | 4821 ms | 23K |
| Agentic Coding | B | Very compromised (needs ~0.3 GB host RAM) | 22.6 tok/s | 12433 ms | 23K |
| Reasoning | A | Tight fit | 40.2 tok/s | 5698 ms | 23K |
| RAG | B | Very compromised (needs ~0.3 GB host RAM) | 22.6 tok/s | 15542 ms | 23K |
How Phi 4 Mini 4B (4B params) fits at each quantization level on Intel Arc A380 6GB (6.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.6 GB | Low | A75 |
Q3_K_S | 3 | 2.0 GB | Low | A75 |
NVFP4 | 4 | 2.2 GB | Medium | A75 |
Q4_K_M | 4 | 2.4 GB | Medium | A75 |
Q5_K_M | 5 | 2.9 GB | High | A75 |
Q6_KBest for your GPU | 6 | 3.3 GB | High | A74 |
Q8_0 | 8 | 4.3 GB | Very High | F0 |
F16 | 16 | 8.2 GB | Maximum | F0 |
Copy-paste commands to run Phi 4 Mini 4B on your machine.
Run
ollama run phi4-miniYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen 2.5 VL 7B | 7B | B | 14.1 tok/s | |
| Qwen 2.5 7B | 7B | B | 14.1 tok/s | |
 Codestral Mamba 7B | 7B | A | 16.8 tok/s | |
 Gemma 4 E2B | 5.1B | A | 24.1 tok/s |
Yes, Intel Arc A380 6GB can run Phi 4 Mini 4B with a A grade (Tight fit). Expected decode speed: 40.2 tok/s.
Phi 4 Mini 4B (4B parameters) requires approximately 5.4 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 4 Mini 4B is Q4_K_M, which balances quality and memory efficiency.
On Intel Arc A380 6GB, Phi 4 Mini 4B achieves approximately 40.2 tokens per second decode speed with a time-to-first-token of 4821ms using Q4_K_M quantization.
For coding workloads, Phi 4 Mini 4B on Intel Arc A380 6GB receives a A grade with 40.2 tok/s and 23K context.
On Intel Arc A380 6GB, Phi 4 Mini 4B can safely use up to 23K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-4-mini-4b-on-arc-a380-6gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: