phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Oct 20, 2026 · Apple M1 Pro
Global Score
64 vs 78
Hardware Fit
100 vs 56
Quality Score
48 vs 87
Hardware
phi3:3.8b qwen3.8-27b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b qwen3.8-27b-mlx
Tokens/sec42.010.8
First chunkN/A8 ms
TTFT142 ms2.6 s
Load time1.1 sN/A
Memory usage16.0 GB21.0 GB
Memory %50%66%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
16/20
Memory
17/30
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
qwen3.8-27b-mlx
Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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