microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

hf.co/openbmb/MiniCPM5-1B-GGUF:F16

OLLAMA GGUF

llama · 1.08B · F16

Good

Aug 25, 2026 · Apple M1 Pro

Global Score

62 vs 71

Hardware Fit

99 vs 100

Quality Score

46 vs 58

Hardware

microsoft/phi-4-mi… hf.co/openbmb/Mini…

MachineMacBook AirMacBook Pro

CPUApple M4Apple M1 Pro

Cores1010

RAM32 GB16 GB

GPUApple M4Apple M1 Pro

OSmacOS 26.3macOS 26.6.2

Archarm64arm64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… hf.co/openbmb/Mini…

Tokens/sec40.388.1

First chunk289 ms38 ms

TTFT289 ms38 ms

Load timeN/A1.6 s

Memory usage2.0 GB3.9 GB

Memory %6%25%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

hf.co/openbmb/MiniCPM5-…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

6/20

Instruction

7/20

Structured

7/15

Math

12/15

Multilingual

7/10

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

hf.co/openbmb/MiniCPM5-…

Reasoning

12/20

Coding

10/20

Instruction

15/20

Structured

11/15

Math

3/15

Multilingual

7/10

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

View microsoft/phi-4-mi… details | View hf.co/openbmb/Mini… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest