qwen3.5-27b-claude-4.6-opus-distilled-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Mar 10, 2026 · Apple M4
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
34 vs 62
Hardware Fit
21 vs 99
Quality Score
39 vs 46
Hardware
qwen3.5-27b-claude… microsoft/phi-4-mi…
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-27b-claude… microsoft/phi-4-mi…
Tokens/sec6.140.3
First chunk7 ms289 ms
TTFT22.9 s289 ms
Load timeN/AN/A
Memory usage19.8 GB2.0 GB
Memory %82%6%
HW Fit Score Breakdown
qwen3.5-27b-claude-4.6-…
Speed
12/50
TTFT
0/20
Memory
9/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5-27b-claude-4.6-…
Reasoning
1/20
Coding
14/20
Instruction
5/20
Structured
8/15
Math
4/15
Multilingual
7/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Adequate 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