gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Apr 1, 2026 · Apple M4
Global Score
81 vs 82
Hardware Fit
82 vs 85
Quality Score
81 vs 81
Hardware
gemma4:12b-mlx openai/gpt-oss-20b
MachineMacBook ProMac mini
CPUApple M2 ProApple M4
Cores1010
RAM16 GB24 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx openai/gpt-oss-20b
Tokens/sec25.331.8
First chunk761 ms32 ms
TTFT7.7 s8.4 s
Load time3.6 s22.7 s
Memory usage7.1 GB0.0 GB
Memory %44%0%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
openai/gpt-oss-20b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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