mlx-community/quantized-gemma-2b-it

LM-STUDIO GGUF

Marginal

Mar 5, 2026 · Apple M4

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

Global Score

45 vs 38

Hardware Fit

100 vs 100

Quality Score

21 vs 12

Hardware

mlx-community/quan… phi-3-mini-128k-in…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mlx-community/quan… phi-3-mini-128k-in…

Tokens/sec44.444.0

First chunk336 ms384 ms

TTFT336 ms385 ms

Load timeN/AN/A

Memory usage0.1 GB2.0 GB

Memory %0%6%

HW Fit Score Breakdown

mlx-community/quantized…

Speed

50/50

TTFT

20/20

Memory

30/30

phi-3-mini-128k-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

mlx-community/quantized…

Reasoning

4/20

Coding

1/20

Instruction

9/20

Structured

4/15

Math

2/15

Multilingual

1/10

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

phi-3-mini-128k-instruct

Reasoning

3/20

Coding

2/20

Instruction

2/20

Structured

1/15

Math

2/15

Multilingual

2/10

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

View mlx-community/quan… details | View phi-3-mini-128k-in… 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