phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score

38 vs 62

Hardware Fit

100 vs 77

Quality Score

12 vs 55

Hardware

phi-3-mini-128k-in… google/gemma-4-e4b

MachineMacBook AirLENOVO 82JQ

CPUApple M4AMD Ryzen 7 5800H

Cores1016

RAM32 GB16 GB

GPUApple M4NVIDIA GeForce RTX 3060 Laptop GPU

OSmacOS 26.3Microsoft Windows 11 家庭版中文版 10.0.26100

Archarm64x64

Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… google/gemma-4-e4b

Tokens/sec44.027.6

First chunk384 ms23 ms

TTFT385 ms480 ms

Load timeN/AN/A

Memory usage2.0 GB13.2 GB

Memory %6%83%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

google/gemma-4-e4b

Speed

48/50

TTFT

20/20

Memory

9/30

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

google/gemma-4-e4b

Reasoning

18/20

Coding

17/20

Instruction

5/20

Structured

3/15

Math

11/15

Multilingual

1/10

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

View phi-3-mini-128k-in… details | View google/gemma-4-e4b 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