microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
62 vs 85
Hardware Fit
99 vs 78
Quality Score
46 vs 88
Hardware
microsoft/phi-4-mi… Kimi-48B:48B
MachineMacBook AirHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4AMD Ryzen 9 9955HX3D 16-Core Processor
Cores1032
RAM32 GB31 GB
GPUApple M4AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
microsoft/phi-4-mi… Kimi-48B:48B
Tokens/sec40.343.0
First chunk289 ms700 ms
TTFT289 ms700 ms
Load timeN/A29.4 s
Memory usage2.0 GB25.8 GB
Memory %6%83%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
8/30
Quality
microsoft/phi-4-mini-re…
Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
Kimi-48B:48B
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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