gemma4:12b-fast
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
85 vs 74
Hardware Fit
80 vs 98
Quality Score
87 vs 63
Hardware
gemma4:12b-fast phi4-mini:latest
MachineASUSNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Gen Intel® Core™ i7-12700Cortex-A78AE
Cores206
RAM30 GB7 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060Integrated / Unknown
OSUbuntu 26.04.1 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modelow-powerbalanced
Performance
gemma4:12b-fast phi4-mini:latest
Tokens/sec75.918.4
First chunk169 ms1078 ms
TTFT30.0 s1.1 s
Load time8.4 s6.4 s
Memory usage1.3 GB2.9 GB
Memory %5%39%
HW Fit Score Breakdown
gemma4:12b-fast
Speed
50/50
TTFT
0/20
Memory
30/30
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
gemma4:12b-fast
Reasoning
18/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak 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