deepseek-r1:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Mar 2, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
22 vs 77
Hardware Fit
50 vs 67
Quality Score
10 vs 81
Hardware
deepseek-r1:14b openai/gpt-oss-20b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:14b openai/gpt-oss-20b
Tokens/sec11.430.5
First chunkN/A18 ms
TTFT30.0 s30.0 s
Load time1.0 sN/A
Memory usage16.5 GB15.8 GB
Memory %52%66%
HW Fit Score Breakdown
deepseek-r1:14b
Speed
20/50
TTFT
0/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
17/30
Quality
deepseek-r1:14b
Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
openai/gpt-oss-20b
Reasoning
19/20
Coding
11/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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