openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Apr 1, 2026 · Apple M4

google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

82 vs 76

Hardware Fit

85 vs 100

Quality Score

81 vs 66

Hardware

openai/gpt-oss-20b google/gemma-3-4b

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

openai/gpt-oss-20b google/gemma-3-4b

Tokens/sec31.839.4

First chunk32 ms468 ms

TTFT8.4 s468 ms

Load time22.7 sN/A

Memory usage0.0 GB2.8 GB

Memory %0%9%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed

50/50

TTFT

5/20

Memory

30/30

google/gemma-3-4b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

openai/gpt-oss-20b

Reasoning

19/20

Coding

14/20

Instruction

9/20

Structured

14/15

Math

15/15

Multilingual

10/10

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

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

View openai/gpt-oss-20b details | View google/gemma-3-4b 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