hermes3:8b
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 6, 2026 · Apple M4
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
74 vs 62
Hardware Fit
94 vs 99
Quality Score
65 vs 46
Hardware
hermes3:8b microsoft/phi-4-mi…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
hermes3:8b microsoft/phi-4-mi…
Tokens/sec22.340.3
First chunk296 ms289 ms
TTFT296 ms289 ms
Load time0.8 sN/A
Memory usage10.2 GB2.0 GB
Memory %32%6%
HW Fit Score Breakdown
hermes3:8b
Speed
44/50
TTFT
20/20
Memory
30/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
hermes3:8b
Reasoning
11/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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