qwen3.6:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
20 vs 62
Hardware Fit
34 vs 99
Quality Score
14 vs 46
Hardware
qwen3.6:27b microsoft/phi-4-mi…
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1210
RAM24 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.6:27b microsoft/phi-4-mi…
Tokens/sec10.640.3
First chunk1344 ms289 ms
TTFT30.0 s289 ms
Load time0.2 sN/A
Memory usage18.1 GB2.0 GB
Memory %75%6%
HW Fit Score Breakdown
qwen3.6:27b
Speed
22/50
TTFT
0/20
Memory
12/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.6:27b
Reasoning
2/20
Coding
1/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
6/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
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