qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 3, 2026 · Apple M4
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
71 vs 62
Hardware Fit
88 vs 99
Quality Score
63 vs 46
Hardware
qwen3.5-4b-mlx 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
qwen3.5-4b-mlx microsoft/phi-4-mi…
Tokens/sec23.140.3
First chunk3279 ms289 ms
TTFT3.3 s289 ms
Load timeN/AN/A
Memory usage2.9 GB2.0 GB
Memory %9%6%
HW Fit Score Breakdown
qwen3.5-4b-mlx
Speed
45/50
TTFT
13/20
Memory
30/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5-4b-mlx
Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate 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