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

LM-STUDIO GGUF

Not Rec.

Mar 5, 2026 · Apple M4

hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16

OLLAMA GGUF

llama · 2.99B · BF16

Good

Aug 25, 2026 · Apple M1 Pro

Global Score

33 vs 76

Hardware Fit

74 vs 92

Quality Score

15 vs 69

Hardware

lmstudio-community… hf.co/bartowski/ai…

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

lmstudio-community… hf.co/bartowski/ai…

Tokens/sec11.529.9

First chunk670 ms105 ms

TTFT670 ms105 ms

Load timeN/A3.4 s

Memory usage3.0 GB8.9 GB

Memory %9%56%

HW Fit Score Breakdown

lmstudio-community/Phi-…

Speed

24/50

TTFT

20/20

Memory

30/30

hf.co/bartowski/ai9star…

Speed

50/50

TTFT

20/20

Memory

22/30

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

hf.co/bartowski/ai9star…

Reasoning

11/20

Coding

13/20

Instruction

12/20

Structured

15/15

Math

10/15

Multilingual

8/10

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

View lmstudio-community… details | View hf.co/bartowski/ai… 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