phi4-mini

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 97% Compare

Global Score

39 /100

Not Rec.

Hardware Fit

66/100

Quality

21/100

Get this model

🦙

Ollama

ollama pull phi4-mini

View on Ollama Library

ollama.com/library/phi4-mini

🤗

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
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 21.8
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
Time to first token How fast the model starts responding — lower is better: 9.6 s
Load time Time to load the model into memory before inference: 3.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.0 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1295

Score breakdown

Speed

31/40

Time to first token

5/30

Memory

30/30

Quality

Reasoning

11/20

Coding

0/20

Instruction following

0/20

Structured output

0/15

Math

5/15

Multilingual

5/10

Category levels

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

Metadata

Spec version: 0.1.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: fc2d2661c8b5bb9a607c9d9aecd4d3e9bca08c1fe9e96fa09576b35ed62c1576

Interpretation

Hardware fit: 66/100. Overall suitability: NOT RECOMMENDED (Global 39/100). Category profile: Reasoning: Adequate, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Weak, Multilingual: Weak.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running