lmstudio-community/Phi-4-reasoning-plus-MLX-4bit

LM-STUDIO GGUF

Not Rec.

Mar 5, 2026 · Apple M4

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score

33 vs 66

Hardware Fit

74 vs 87

Quality Score

15 vs 57

Hardware

lmstudio-community… granite-3.3-2b-ins…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

lmstudio-community… granite-3.3-2b-ins…

Tokens/sec11.518.3

First chunk670 ms541 ms

TTFT670 ms541 ms

Load timeN/AN/A

Memory usage3.0 GB4.7 GB

Memory %9%15%

HW Fit Score Breakdown

lmstudio-community/Phi-…

Speed

24/50

TTFT

20/20

Memory

30/30

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

Quality

lmstudio-community/Phi-…

Reasoning

8/20

Coding

1/20

Instruction

1/20

Structured

1/15

Math

1/15

Multilingual

3/10

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

granite-3.3-2b-instruct

Reasoning

10/20

Coding

10/20

Instruction

14/20

Structured

14/15

Math

2/15

Multilingual

7/10

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

View lmstudio-community… details | View granite-3.3-2b-ins… 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