gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
86 vs 46
Hardware Fit
78 vs 61
Quality Score
90 vs 40
Hardware
gemma4:12b llama3.1:8b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-X925Cortex-A78AE
Cores206
RAM122 GB7 GB
GPUDevice 2e12Integrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modeperformancebalanced
Performance
gemma4:12b llama3.1:8b
Tokens/sec26.37.8
First chunk545 ms1625 ms
TTFT545 ms1.6 s
Load time9.5 s21.8 s
Memory usage8.4 GB5.2 GB
Memory %7%71%
HW Fit Score Breakdown
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
Quality
gemma4:12b
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor 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