deepseek-r1:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Mar 2, 2026 · Apple M4
gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
22 vs 59
Hardware Fit
50 vs 100
Quality Score
10 vs 42
Hardware
deepseek-r1:14b gemma3:1b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:14b gemma3:1b
Tokens/sec11.434.0
First chunkN/A1876 ms
TTFT30.0 s1.9 s
Load time1.0 s1.7 s
Memory usage16.5 GB0.8 GB
Memory %52%11%
HW Fit Score Breakdown
deepseek-r1:14b
Speed
20/50
TTFT
0/20
Memory
30/30
gemma3:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
deepseek-r1:14b
Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
gemma3:1b
Reasoning
7/20
Coding
5/20
Instruction
15/20
Structured
7/15
Math
1/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Weak Math: Poor Multilingual: Adequate
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