google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

llama2:7b

OLLAMA GGUF

llama · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

76 vs 55

Hardware Fit

100 vs 99

Quality Score

66 vs 36

Hardware

google/gemma-3-4b llama2:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

google/gemma-3-4b llama2:7b

Tokens/sec39.425.1

First chunk468 msN/A

TTFT468 ms228 ms

Load timeN/A0.4 s

Memory usage2.8 GB5.8 GB

Memory %9%18%

HW Fit Score Breakdown

google/gemma-3-4b

Speed

50/50

TTFT

20/20

Memory

30/30

llama2:7b

Speed

39/50

TTFT

30/20

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

llama2:7b

Reasoning

4/20

Coding

3/20

Instruction

13/20

Structured

8/15

Math

1/15

Multilingual

7/10

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

View google/gemma-3-4b details | View llama2:7b 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