phi4:14b

phi3 · 14.7B · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 60% Compare

Global Score

65 /100

Good

Hardware Fit

77/100

Quality

57/100

Get this model

🦙

Ollama

ollama pull phi4:14b

View on Ollama Library

ollama.com/library/phi4

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64

Performance

Tokens/sec Tokens generated per second — higher is better: 11.1
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
Time to first token How fast the model starts responding — lower is better: 515 ms
Load time Time to load the model into memory before inference: 9.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 13.4 GB (42%)
Total tokens Total number of tokens generated across all benchmark prompts: 1135

Score breakdown

Speed

17/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

16/20

Coding

0/20

Instruction following

11/20

Structured output

13/15

Math

7/15

Multilingual

10/10

Category levels

Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

Metadata

Spec version: 0.1.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 7148c43ecbeefb47d060f8c450919452a5345a791d6b04013025efbfcf3dc567

Interpretation

Hardware fit: 77/100. Overall suitability: GOOD (Global 65/100). Category profile: Reasoning: Strong, Coding: Poor, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running