qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
53 vs 64
Hardware Fit
72 vs 100
Quality Score
45 vs 48
Hardware
qwen3.5:9b phi3:3.8b
MachineMacBook ProMacBook Air
CPUApple M1 MaxApple M4
Cores1010
RAM32 GB32 GB
GPUApple M1 MaxApple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:9b phi3:3.8b
Tokens/sec18.642.0
First chunk403 msN/A
TTFT10.2 s142 ms
Load time4.3 s1.1 s
Memory usage9.1 GB16.0 GB
Memory %28%50%
HW Fit Score Breakdown
qwen3.5:9b
Speed
38/50
TTFT
4/20
Memory
30/30
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak 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