Phi-4

What is Phi-4?

Phi-4 is Microsoft's open-weights language model. Released in 2024-12, it ships in 1 size (14B) and is licensed MIT. The most popular use case is strong 14B on reasoning benchmarks.

VRAM and hardware

The 14B size fits in 9 GB of VRAM.

Size	Min VRAM (Q4_K_M)	Recommended VRAM	Tokens/sec on 3090
14B	9 GB	14 GB	~22 tok/s

How to run Phi-4 locally

Option 1: Ollama (simplest)

ollama pull phi-4
ollama run phi-4

Option 2: Mullama (production)

mullama pull phi-4
mullama run phi-4

Option 3: llama.cpp (CLI)

# Download a GGUF from Hugging Face (search "phi-4 gguf")
./llama-cli -m phi-4.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("phi-4.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

What you can build with Phi-4

• chat
• reasoning
• math

Hardware it fits on

• Apple Silicon (8GB): 14B in MLX
• Apple Silicon (16GB): 14B in MLX
• Apple Silicon (32GB): 14B in MLX or GGUF
• Apple Silicon (64GB+): 14B in MLX
• RTX 3090 (24GB): 14B at Q4_K_M
• RTX 4090 (24GB): same as 3090, ~30% faster
• RTX 5090 (32GB): 14B at Q8_0
• 2× RTX 6000 Ada (96GB total): 14B at Q4_K_M

Related models in the Phi family

• Phi-3 — Mini 3.8B, Medium 14B · small chat, edge deployment
• Phi-4 Mini — 3.8B · small chat with function calling and tool use
• Phi-4 Reasoning — 14B · strong reasoning in a 14B model

Other models you might consider

• Llama 3.1 (Meta) — 8B, general-purpose chat, agentic workflows, code
• Llama 3.2 (Meta) — 1B, low-end hardware, mobile, edge deployment
• Llama 3.2 Vision (Meta) — 11B, vision + chat on desktop GPUs
• Llama 3.3 (Meta) — 70B, best-in-class 70B for desktops
• Llama 4 (Meta) — Scout 17B (109B MoE), vision + long context (10M tokens)
• Qwen 2.5 (Alibaba) — 0.5B, strongest 7B-32B on consumer hardware