qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 11, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 11, 2026 · Apple M4
Global Score
83 vs 95
Hardware Fit
73 vs 99
Quality Score
87 vs 93
Hardware
qwen3:14b openai/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 openai/gpt-oss-20b
Tokens/sec11.129.3
First chunk500 ms21 ms
TTFT500 ms1.8 s
Load time7.3 s18.5 s
Memory usage9.4 GB0.0 GB
Memory %39%0%
HW Fit Score Breakdown
qwen3:14b
Speed
25/50
TTFT
20/20
Memory
28/30
openai/gpt-oss-20b
Speed
50/50
TTFT
19/20
Memory
30/30
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
openai/gpt-oss-20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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