openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Apr 1, 2026 · Apple M4
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 19, 2026 · Apple M4
Global Score
82 vs 82
Hardware Fit
85 vs 71
Quality Score
81 vs 86
Hardware
openai/gpt-oss-20b qwen3:14b
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM24 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b qwen3:14b
Tokens/sec31.810.3
First chunk32 ms513 ms
TTFT8.4 s513 ms
Load time22.7 s7.2 s
Memory usage0.0 GB9.4 GB
Memory %0%39%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
5/20
Memory
30/30
qwen3:14b
Speed
23/50
TTFT
20/20
Memory
28/30
Quality
openai/gpt-oss-20b
Reasoning
19/20
Coding
14/20
Instruction
9/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:14b
Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
12/15
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