phi-3.5-mini-instruct

phi3 · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 4, 2026

Top 75% Compare

Global Score

55 /100

Marginal

Hardware Fit

100/100

Quality

36/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

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: 43.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 359 ms
Time to first token How fast the model starts responding — lower is better: 359 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 2.0 GB (6%)
Total tokens Total number of tokens generated across all benchmark prompts: 1656

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

11/20

Coding

4/20

Instruction following

7/20

Structured output

1/15

Math

7/15

Multilingual

6/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: 5cd100126a82da36399fb46dd63f11433ba23a77a89d2bb00211b1a8a206ef4b

Interpretation

Hardware fit: 100/100. Overall suitability: MARGINAL (Global 55/100). Category profile: Reasoning: Adequate, Coding: Poor, Instruction Following: Weak, Structured Output: Poor, Math: Weak, Multilingual: Adequate.

Bench Environment

Power: AC CPU load: avg 15% (peak 17%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest