gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_M
OLLAMA GGUFgpt-oss · 20.9B · unknown
Aug 24, 2026 · Apple M1 Pro
Global Score
91 vs 86
Hardware Fit
96 vs 75
Quality Score
89 vs 90
Hardware
gemma4:12b-mlx hf.co/unsloth/gpt-…
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M2 ProApple M1 Pro
OSmacOS 26.5macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx hf.co/unsloth/gpt-…
Tokens/sec24.735.9
First chunk610 ms1082 ms
TTFT610 ms5.2 s
Load time3.6 s8.2 s
Memory usage7.1 GB11.1 GB
Memory %45%69%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
hf.co/unsloth/gpt-oss-2…
Speed
50/50
TTFT
10/20
Memory
15/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
hf.co/unsloth/gpt-oss-2…
Reasoning
19/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
15/15
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