phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
starling-lm:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 6, 2026 · Apple M4
Global Score
64 vs 65
Hardware Fit
100 vs 96
Quality Score
48 vs 52
Hardware
phi3:3.8b starling-lm:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b starling-lm:7b
Tokens/sec42.023.8
First chunkN/A232 ms
TTFT142 ms232 ms
Load time1.1 s0.4 s
Memory usage16.0 GB5.3 GB
Memory %50%17%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
starling-lm:7b
Speed
46/50
TTFT
20/20
Memory
30/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
starling-lm:7b
Reasoning
10/20
Coding
13/20
Instruction
8/20
Structured
3/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Adequate 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