openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
Global Score
91 vs 84
Hardware Fit
90 vs 64
Quality Score
91 vs 92
Hardware
openai/gpt-oss-20b unsloth/gemma-4-26…
MachineMacBook ProMac mini
CPUApple M3 MaxApple M4
Cores1610
RAM128 GB24 GB
GPUApple M3 MaxApple M4
OSmacOS 27.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b unsloth/gemma-4-26…
Tokens/sec95.116.5
First chunk3 ms32 ms
TTFT2.5 s2.2 s
Load time9.2 sN/A
Memory usage0.0 GB19.3 GB
Memory %0%80%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
unsloth/gemma-4-26b-a4b…
Speed
36/50
TTFT
18/20
Memory
10/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
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