phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
77 vs 72
Hardware Fit
74 vs 71
Quality Score
78 vs 72
Hardware
phi4:14b ministral-3:8b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
phi4:14b ministral-3:8b
Tokens/sec22.919.8
First chunk198 ms269 ms
TTFT198 ms269 ms
Load time10.3 s10.7 s
Memory usage14.7 GB13.7 GB
Memory %12%86%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
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-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate 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