gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
85 vs 78
Hardware Fit
95 vs 47
Quality Score
81 vs 92
Hardware
gemma4:e4b-mlx gemma4:31b
MachineMacBook ProAZW GTR Pro
CPUApple M2 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M2 ProRadeon 8060S
OSmacOS 26.5Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:e4b-mlx gemma4:31b
Tokens/sec47.39.8
First chunk258 ms873 ms
TTFT258 ms873 ms
Load time5.1 s7.0 s
Memory usage7.9 GB68.3 GB
Memory %49%55%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
Quality
gemma4:e4b-mlx
Reasoning
15/20
Coding
18/20
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
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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