gemma4:12b-fast
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
85 vs 86
Hardware Fit
80 vs 78
Quality Score
87 vs 89
Hardware
gemma4:12b-fast Kimi-48B:48B
MachineASUSGMKtec NucBox EVO-T2S
CPUIntel Gen Intel® Core™ i7-12700Intel Core™ Ultra X7 358H
Cores2016
RAM30 GB64 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060Intel(R) Arc(TM) B390 GPU
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
gemma4:12b-fast Kimi-48B:48B
Tokens/sec75.923.1
First chunk169 ms752 ms
TTFT30.0 s752 ms
Load time8.4 s22.2 s
Memory usage1.3 GB25.5 GB
Memory %5%40%
HW Fit Score Breakdown
gemma4:12b-fast
Speed
50/50
TTFT
0/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
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
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
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