mlx-community/Llama-3.2-1B-Instruct-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
57 vs 59
Hardware Fit
100 vs 100
Quality Score
39 vs 41
Hardware
mlx-community/Llam… phi:2.7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/Llam… phi:2.7b
Tokens/sec126.456.6
First chunk139 msN/A
TTFT139 ms110 ms
Load timeN/A0.4 s
Memory usage0.3 GB2.2 GB
Memory %1%7%
HW Fit Score Breakdown
mlx-community/Llama-3.2…
Speed
50/50
TTFT
20/20
Memory
30/30
phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
mlx-community/Llama-3.2…
Reasoning
5/20
Coding
3/20
Instruction
15/20
Structured
10/15
Math
1/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Adequate Math: Poor Multilingual: Adequate
phi:2.7b
Reasoning
7/20
Coding
4/20
Instruction
9/20
Structured
11/15
Math
8/15
Multilingual
2/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Poor
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