Skip to content
localmodel.run

text model · phi · Windows

Can I run Phi-4-mini 3.8B on Nvidia GeForce RTX 3090 (24GB)?

Compatibility verdict VRAM threshold engine
Yes, it runsGPU accelerated

Yes. Phi-4-mini 3.8B runs on Nvidia GeForce RTX 3090 (24GB) at Q4_K_M (~3.8 GB of ~23 GB usable).

Needs ~3.8 GB Device usable ~23 GB

Runs at Q4_K_M using ~3.8 GB of ~23 GB usable. You have room for FP16 for higher quality.

Q4_K_M needed
~3.8 GB
Usable on device
~23 GB
Device memory
24 GB
Best quant
Q4_K_M

Run it

Install commands Windows

Pick your tool. All three load the same Q4_K_M weights.

Ollama
$ ollama run phi4-mini:3.8b
llama.cpp
$ llama-cli -hf bartowski/microsoft_Phi-4-mini-instruct-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/microsoft_Phi-4-mini-instruct-GGUF

AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Model phi
Parameters
3.8B
Q4_K_M size
2.49 GB
Q8_0 size
4.08 GB
Context
128k
Ollama tag
phi4-mini:3.8b
Full Phi-4-mini 3.8B requirements →
Device Windows
Memory
24 GB vram
Usable for weights
~23 GB
Best runtime
vLLM (Linux) / Ollama (CUDA)
Best models for Nvidia GeForce RTX 3090 (24GB) →

You could also run

Run Phi-4-mini 3.8B on other hardware

FAQ

Can Nvidia GeForce RTX 3090 (24GB) run Phi-4-mini 3.8B?

Yes. Phi-4-mini 3.8B runs on Nvidia GeForce RTX 3090 (24GB) at Q4_K_M (~3.8 GB of ~23 GB usable).

How much memory does Phi-4-mini 3.8B need?

Nvidia GeForce RTX 3090 (24GB) has room to spare. At Q4_K_M the weights are ~2.49 GB; with KV cache and runtime overhead, budget ~3.8 GB at a 4k context.

What is the best tool to run Phi-4-mini 3.8B on Windows?

LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Sources

Memory figures are estimates. See methodology.