gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
llama-3.2-1b-instruct
LM-STUDIO GGUFllama · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
91 vs 50
Hardware Fit
96 vs 79
Quality Score
89 vs 37
Hardware
gemma4:12b-mlx llama-3.2-1b-instr…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M2 ProIntel Core™ i5-5300U
Cores104
RAM16 GB16 GB
GPUApple M2 ProIntel(R) HD Graphics 5500
OSmacOS 26.5Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx llama-3.2-1b-instr…
Tokens/sec24.79.9
First chunk610 ms1668 ms
TTFT610 ms1.7 s
Load time3.6 sN/A
Memory usage7.1 GB0.8 GB
Memory %45%5%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
llama-3.2-1b-instruct
Speed
32/50
TTFT
20/20
Memory
27/30
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
llama-3.2-1b-instruct
Reasoning
4/20
Coding
3/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor 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