qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 11, 2026 · Apple M4
gemma4:e4b
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 84
Hardware Fit
73 vs 98
Quality Score
87 vs 78
Hardware
qwen3:14b gemma4:e4b
MachineMac miniAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3:14b gemma4:e4b
Tokens/sec11.153.0
First chunk500 ms214 ms
TTFT500 ms214 ms
Load time7.3 s3.1 s
Memory usage9.4 GB15.0 GB
Memory %39%12%
HW Fit Score Breakdown
qwen3:14b
Speed
25/50
TTFT
20/20
Memory
28/30
gemma4:e4b
Speed
48/50
TTFT
20/20
Memory
30/30
Quality
qwen3:14b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:e4b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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