phi3:3.8b

phi3 · 3.8B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 2, 2026

Top 44% Compare

Global Score

69 /100

Good

Hardware Fit

100/100

Quality

48/100

Get this model

🦙

Ollama

ollama pull phi3:3.8b

View on Ollama Library

ollama.com/library/phi3

🤗

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: 42.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
Time to first token How fast the model starts responding — lower is better: 142 ms
Load time Time to load the model into memory before inference: 1.1 s
Memory usage RAM consumed during inference — percentage of total system memory: 16.0 GB (50%)
Total tokens Total number of tokens generated across all benchmark prompts: 1219

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

12/20

Coding

3/20

Instruction following

11/20

Structured output

10/15

Math

5/15

Multilingual

7/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 3e5cbd22d3e6560ca24d14c86ab1b818dc5b9c6ad045fe2c4d2a9f477433a46a

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 69/100). Category profile: Reasoning: Adequate, Coding: Poor, Instruction Following: Adequate, Structured Output: Adequate, Math: Weak, Multilingual: Adequate.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running