qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
tinyllama
OLLAMA GGUFMar 6, 2026 · Apple M4
Global Score
58 vs 43
Hardware Fit
82 vs 100
Quality Score
48 vs 19
Hardware
qwen3:14b tinyllama
MachineMacBook ProMacBook Air
CPUApple M1 MaxApple M4
Cores1010
RAM32 GB32 GB
GPUApple M1 MaxApple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b tinyllama
Tokens/sec24.4133.4
First chunk294 ms61 ms
TTFT7.9 s61 ms
Load time3.7 s0.5 s
Memory usage13.8 GB0.2 GB
Memory %43%1%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
tinyllama
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
tinyllama
Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
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