microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
nous-hermes2:latest
OLLAMA GGUFllama · 11B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
62 vs 68
Hardware Fit
99 vs 87
Quality Score
46 vs 60
Hardware
microsoft/phi-4-mi… nous-hermes2:latest
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
microsoft/phi-4-mi… nous-hermes2:latest
Tokens/sec40.315.9
First chunk289 msN/A
TTFT289 ms345 ms
Load timeN/A0.4 s
Memory usage2.0 GB6.6 GB
Memory %6%21%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
nous-hermes2:latest
Speed
27/50
TTFT
30/20
Memory
30/30
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
nous-hermes2:latest
Reasoning
11/20
Coding
9/20
Instruction
12/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak 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