qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 6bit
Jul 17, 2026 · Apple M5 Max
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
87 vs 62
Hardware Fit
90 vs 99
Quality Score
86 vs 46
Hardware
qwen/qwen3.6-35b-a3b 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
qwen/qwen3.6-35b-a3b microsoft/phi-4-mi…
Tokens/sec86.540.3
First chunk9 ms289 ms
TTFT175 ms289 ms
Load timeN/AN/A
Memory usage37.9 GB2.0 GB
Memory %59%6%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
20/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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