qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Mar 10, 2026 · Apple M4
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
66 vs 64
Hardware Fit
34 vs 100
Quality Score
80 vs 48
Hardware
qwen3.5:27b microsoft/phi-4-mi…
MachineMac miniMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM24 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:27b microsoft/phi-4-mi…
Tokens/sec4.090.3
First chunk1655 ms198 ms
TTFT1.7 s198 ms
Load time12.9 sN/A
Memory usage21.3 GB2.0 GB
Memory %89%3%
HW Fit Score Breakdown
qwen3.5:27b
Speed
8/50
TTFT
20/20
Memory
6/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:27b
Reasoning
16/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
microsoft/phi-4-mini-re…
Reasoning
7/20
Coding
7/20
Instruction
7/20
Structured
7/15
Math
13/15
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