phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

laguna-xs-2.1

OLLAMA GGUF

Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score

38 vs 84

Hardware Fit

100 vs 100

Quality Score

12 vs 77

Hardware

phi-3-mini-128k-in… laguna-xs-2.1

MachineMacBook AirAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM32 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedlow-power

Performance

phi-3-mini-128k-in… laguna-xs-2.1

Tokens/sec44.065.9

First chunk384 ms281 ms

TTFT385 ms281 ms

Load timeN/A9.9 s

Memory usage2.0 GB30.1 GB

Memory %6%24%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

laguna-xs-2.1

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

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

laguna-xs-2.1

Reasoning

8/20

Coding

18/20

Instruction

16/20

Structured

14/15

Math

11/15

Multilingual

10/10

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

View phi-3-mini-128k-in… details | View laguna-xs-2.1 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