phi3:14b
OLLAMA GGUFphi3 · 14.0B · Q4_0
Mar 2, 2026 · Apple M4
qwen3:4b
OLLAMA GGUFqwen3 · 4.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
63 vs 29
Hardware Fit
83 vs 86
Quality Score
55 vs 4
Hardware
phi3:14b qwen3:4b
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
phi3:14b qwen3:4b
Tokens/sec12.717.9
First chunkN/A1010 ms
TTFT434 ms6.4 s
Load time0.9 s9.5 s
Memory usage17.7 GB3.0 GB
Memory %55%40%
HW Fit Score Breakdown
phi3:14b
Speed
23/50
TTFT
30/20
Memory
30/30
qwen3:4b
Speed
50/50
TTFT
8/20
Memory
28/30
Quality
phi3:14b
Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
qwen3:4b
Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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