gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Nov 4, 2026 · Intel Core™ i7-9700
Global Score
86 vs 71
Hardware Fit
80 vs 90
Quality Score
89 vs 63
Hardware
gemma4:12b llama3.2:3b
MachineASUSVMware, Inc. VMware Virtual Platform
CPUIntel Gen Intel® Core™ i7-12700Intel Core™ i7-9700
Cores204
RAM30 GB16 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060Integrated / Unknown
OSUbuntu 26.04.1 LTSUbuntu 24.04.5 LTS
Archx64x64
Power Modelow-powerunknown
Performance
gemma4:12b llama3.2:3b
Tokens/sec74.413.0
First chunk152 ms536 ms
TTFT30.0 s536 ms
Load time0.0 s82.5 s
Memory usage0.8 GB2.4 GB
Memory %3%15%
HW Fit Score Breakdown
gemma4:12b
Speed
50/50
TTFT
0/20
Memory
30/30
llama3.2:3b
Speed
40/50
TTFT
20/20
Memory
30/30
Quality
gemma4:12b
Reasoning
18/20
Coding
15/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.2:3b
Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong 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