gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
Global Score
78 vs 66
Hardware Fit
72 vs 40
Quality Score
81 vs 77
Hardware
gemma4:e4b-mlx gemma4:31b
MachineMacBook ProASUSTeK COMPUTER INC. GX10
CPUApple M2 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M2 ProDevice 2e12
OSmacOS 26.5Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gemma4:e4b-mlx gemma4:31b
Tokens/sec26.910.7
First chunk222 ms983 ms
TTFT222 ms20.3 s
Load time0.1 s8.8 s
Memory usage15.4 GB21.4 GB
Memory %96%18%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
gemma4:31b
Speed
10/50
TTFT
0/20
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
gemma4:31b
Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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