qwen3:4b
OLLAMA GGUFqwen3 · 4.0B · Q4_K_M
Mar 1, 2026 · Apple M4
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
47 vs 77
Hardware Fit
53 vs 74
Quality Score
45 vs 78
Hardware
qwen3:4b phi4:14b
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modeunknownperformance
Performance
qwen3:4b phi4:14b
Tokens/sec11.322.9
First chunkN/A198 ms
TTFT9.2 s198 ms
Load time0.1 s10.3 s
Memory usage7.2 GB14.7 GB
Memory %23%12%
HW Fit Score Breakdown
qwen3:4b
Speed
17/50
TTFT
6/20
Memory
30/30
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
Quality
qwen3:4b
Reasoning
4/20
Coding
6/20
Instruction
8/20
Structured
6/15
Math
12/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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