Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
78 vs 76
Hardware Fit
72 vs 100
Quality Score
81 vs 66

Hardware

gemma4:e4b-mlx google/gemma-3-4b
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx google/gemma-3-4b
Tokens/sec26.939.4
First chunk222 ms468 ms
TTFT222 ms468 ms
Load time0.1 sN/A
Memory usage15.4 GB2.8 GB
Memory %96%9%

HW Fit Score Breakdown

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
2/30

google/gemma-3-4b

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

gemma4:e4b-mlx

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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 gemma4:e4b-mlx 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