google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

Global Score

76 vs 76

Hardware Fit

100 vs 100

Quality Score

66 vs 65

Hardware

google/gemma-3-4b llama3.2:latest

MachineMacBook AirMicro-Star International Co., Ltd. MS-7B79

CPUApple M4AMD Ryzen 5 2600X Six-Core Processor

Cores1012

RAM32 GB16 GB

GPUApple M4NVIDIA GeForce GTX 1080

OSmacOS 26.3Microsoft Windows 11 Famille 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

google/gemma-3-4b llama3.2:latest

Tokens/sec39.457.0

First chunk468 ms264 ms

TTFT468 ms264 ms

Load timeN/A9.7 s

Memory usage2.8 GB2.6 GB

Memory %9%16%

HW Fit Score Breakdown

google/gemma-3-4b

Speed

50/50

TTFT

20/20

Memory

30/30

llama3.2:latest

Speed

50/50

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

llama3.2:latest

Reasoning

11/20

Coding

15/20

Instruction

15/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

View google/gemma-3-4b details | View llama3.2: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