gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
tinyllama
OLLAMA GGUFMar 6, 2026 · Apple M4
Global Score
87 vs 43
Hardware Fit
79 vs 100
Quality Score
90 vs 19
Hardware
gpt-oss:20b tinyllama
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b tinyllama
Tokens/sec26.4133.4
First chunk505 ms61 ms
TTFT6.7 s61 ms
Load time10.5 s0.5 s
Memory usage13.1 GB0.2 GB
Memory %55%1%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
23/30
tinyllama
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
tinyllama
Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
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