qwen36-distill-apex
OLLAMA GGUFJul 17, 2026 · Apple M5 Max
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
36 vs 62
Hardware Fit
100 vs 99
Quality Score
8 vs 46
Hardware
qwen36-distill-apex microsoft/phi-4-mi…
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen36-distill-apex microsoft/phi-4-mi…
Tokens/sec55.240.3
First chunk210 ms289 ms
TTFT210 ms289 ms
Load time4.8 sN/A
Memory usage0.9 GB2.0 GB
Memory %2%6%
HW Fit Score Breakdown
qwen36-distill-apex
Speed
50/50
TTFT
20/20
Memory
30/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen36-distill-apex
Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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