microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
62 vs 80
Hardware Fit
99 vs 95
Quality Score
46 vs 73
Hardware
microsoft/phi-4-mi… lfm2.5:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
microsoft/phi-4-mi… lfm2.5:8b
Tokens/sec40.398.5
First chunk289 ms167 ms
TTFT289 ms2.5 s
Load timeN/A3.0 s
Memory usage2.0 GB6.0 GB
Memory %6%37%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
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
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate 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