phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Mar 2, 2026 · Apple M4
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
75 vs 84
Hardware Fit
79 vs 97
Quality Score
73 vs 79
Hardware
phi4:14b qwen3:8b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi4:14b qwen3:8b
Tokens/sec11.0208.0
First chunkN/A82 ms
TTFT532 ms1.3 s
Load time0.7 s1.5 s
Memory usage13.4 GB9.6 GB
Memory %42%20%
HW Fit Score Breakdown
phi4:14b
Speed
19/50
TTFT
30/20
Memory
30/30
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
Quality
phi4:14b
Reasoning
15/20
Coding
18/20
Instruction
10/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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