gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
Global Score
71 vs 87
Hardware Fit
76 vs 83
Quality Score
69 vs 88
Hardware
gemma4:12b-mlx gpt-oss:20b
MachineMacBook ProMac mini
CPUApple M1 ProApple M4
Cores1010
RAM16 GB24 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx gpt-oss:20b
Tokens/sec25.024.3
First chunk787 ms529 ms
TTFT30.0 s4.5 s
Load time4.0 s11.2 s
Memory usage7.1 GB13.1 GB
Memory %45%55%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
Quality
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
Structured
14/15
Math
15/15
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