phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
77 vs 71
Hardware Fit
74 vs 99
Quality Score
78 vs 59
Hardware
phi4:14b ministral-3:3b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
phi4:14b ministral-3:3b
Tokens/sec22.942.2
First chunk198 ms189 ms
TTFT198 ms189 ms
Load time10.3 s1.2 s
Memory usage14.7 GB7.0 GB
Memory %12%22%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
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
ministral-3:3b
Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak 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