gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
78 vs 53
Hardware Fit
72 vs 99
Quality Score
81 vs 33
Hardware
gemma4:e4b-mlx mlx-community/Nanb…
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 mlx-community/Nanb…
Tokens/sec26.925.4
First chunk222 ms266 ms
TTFT222 ms266 ms
Load time0.1 sN/A
Memory usage15.4 GB0.0 GB
Memory %96%0%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
mlx-community/Nanbeige4…
Speed
49/50
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
mlx-community/Nanbeige4…
Reasoning
10/20
Coding
7/20
Instruction
1/20
Structured
1/15
Math
11/15
Multilingual
3/10
Reasoning: Adequate Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Weak
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest