phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
mlx-community/stablelm-2-zephyr-1_6b-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
64 vs 50
Hardware Fit
100 vs 100
Quality Score
48 vs 29
Hardware
phi3:3.8b mlx-community/stab…
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 mlx-community/stab…
Tokens/sec42.093.6
First chunkN/A166 ms
TTFT142 ms166 ms
Load time1.1 sN/A
Memory usage16.0 GB0.7 GB
Memory %50%2%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
mlx-community/stablelm-…
Speed
50/50
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
mlx-community/stablelm-…
Reasoning
7/20
Coding
2/20
Instruction
9/20
Structured
3/15
Math
4/15
Multilingual
4/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Weak
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