phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3:4b
OLLAMA GGUFqwen3 · 4.0B · Q4_K_M
Mar 1, 2026 · Apple M4
Global Score
77 vs 47
Hardware Fit
74 vs 53
Quality Score
78 vs 45
Hardware
phi4:14b qwen3:4b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformanceunknown
Performance
phi4:14b qwen3:4b
Tokens/sec22.911.3
First chunk198 msN/A
TTFT198 ms9.2 s
Load time10.3 s0.1 s
Memory usage14.7 GB7.2 GB
Memory %12%23%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3:4b
Speed
17/50
TTFT
6/20
Memory
30/30
Quality
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
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
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