text model · phi · Windows
Can I run Phi-4-mini 3.8B on Nvidia GeForce RTX 3090 (24GB)?
Yes. Phi-4-mini 3.8B runs on Nvidia GeForce RTX 3090 (24GB) at Q4_K_M (~3.8 GB of ~23 GB usable).
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
Pick your tool. All three load the same Q4_K_M weights.
ollama run phi4-mini:3.8b llama-cli -hf bartowski/microsoft_Phi-4-mini-instruct-GGUF:Q4_K_M 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.
- Parameters
- 3.8B
- Q4_K_M size
- 2.49 GB
- Q8_0 size
- 4.08 GB
- Context
- 128k
- Ollama tag
- phi4-mini:3.8b
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
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.