qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 11, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
Global Score
83 vs 83
Hardware Fit
73 vs 65
Quality Score
87 vs 90
Hardware
qwen3:14b gpt-oss:20b
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM24 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b gpt-oss:20b
Tokens/sec11.117.1
First chunk500 ms705 ms
TTFT500 ms10.2 s
Load time7.3 s23.1 s
Memory usage9.4 GB13.1 GB
Memory %39%55%
HW Fit Score Breakdown
qwen3:14b
Speed
25/50
TTFT
20/20
Memory
28/30
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
Quality
qwen3:14b
Reasoning
17/20
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
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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