qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
Global Score
90 vs 83
Hardware Fit
97 vs 60
Quality Score
87 vs 93
Hardware
qwen3:14b gemma4:31b
MachineMacBook ProASUSTeK COMPUTER INC. GX10
CPUApple M1 MaxCortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M1 MaxDevice 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3:14b gemma4:31b
Tokens/sec24.010.9
First chunk300 ms681 ms
TTFT300 ms681 ms
Load time3.6 s16.6 s
Memory usage13.8 GB21.4 GB
Memory %43%18%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
20/20
Memory
30/30
gemma4:31b
Speed
10/50
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
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
17/20
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