google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

Global Score

76 vs 73

Hardware Fit

100 vs 93

Quality Score

66 vs 65

Hardware

google/gemma-3-4b lfm2.5:latest

MachineMacBook AirLENOVO 20L7CTO1WW

CPUApple M4Intel Core™ i5-8350U

Cores108

RAM32 GB23 GB

GPUApple M4Kaby Lake-R GT2 [UHD Graphics 620]

OSmacOS 26.3Fedora Linux 44

Archarm64x64

Power Modebalancedperformance

Performance

google/gemma-3-4b lfm2.5:latest

Tokens/sec39.418.3

First chunk468 ms981 ms

TTFT468 ms981 ms

Load timeN/A8.0 s

Memory usage2.8 GB4.9 GB

Memory %9%21%

HW Fit Score Breakdown

google/gemma-3-4b

Speed

50/50

TTFT

20/20

Memory

30/30

lfm2.5:latest

Speed

43/50

TTFT

20/20

Memory

30/30

Quality

google/gemma-3-4b

Reasoning

10/20

Coding

17/20

Instruction

13/20

Structured

12/15

Math

4/15

Multilingual

10/10

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

lfm2.5:latest

Reasoning

2/20

Coding

11/20

Instruction

14/20

Structured

13/15

Math

15/15

Multilingual

10/10

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

View google/gemma-3-4b details | View lfm2.5:latest 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