gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Mar 5, 2026 · AMD Ryzen 9 8945HS
Global Score
63 vs 62
Hardware Fit
62 vs 91
Quality Score
63 vs 50
Hardware
gemma4:12b llama3.2:1b
MachineMacBook ProASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV
CPUApple M1 ProAMD Ryzen 9 8945HS
Cores1016
RAM16 GB15 GB
GPUApple M1 ProNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OSmacOS 26.6.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b llama3.2:1b
Tokens/sec15.3170.2
First chunk1142 ms142 ms
TTFT30.0 s142 ms
Load time5.4 s3.2 s
Memory usage7.6 GB1.6 GB
Memory %47%11%
HW Fit Score Breakdown
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
21/30
Quality
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
llama3.2:1b
Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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