Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

gemma-3-1b-it

LM-STUDIO GGUF

gemma3 · 1B · Q4_K_M

Marginal

Mar 5, 2026 · Intel Core™ i5-5300U

Global Score
78 vs 59
Hardware Fit
72 vs 76
Quality Score
81 vs 52

Hardware

gemma4:e4b-mlx gemma-3-1b-it
MachineMacBook ProLENOVO 20BUS00700
CPUApple M2 ProIntel Core™ i5-5300U
Cores104
RAM16 GB16 GB
GPUApple M2 ProIntel(R) HD Graphics 5500
OSmacOS 26.5Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx gemma-3-1b-it
Tokens/sec26.98.7
First chunk222 ms2078 ms
TTFT222 ms2.1 s
Load time0.1 sN/A
Memory usage15.4 GB0.8 GB
Memory %96%5%

HW Fit Score Breakdown

gemma4:e4b-mlx

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

gemma-3-1b-it

Speed
29/50
TTFT
19/20
Memory
28/30

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

gemma-3-1b-it

Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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