llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
46 vs 86
Hardware Fit
61 vs 78
Quality Score
40 vs 90
Hardware
llama3.1:8b gemma4:12b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperNVIDIA NVIDIA_DGX_Spark
CPUCortex-A78AECortex-X925
Cores620
RAM7 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
llama3.1:8b gemma4:12b
Tokens/sec7.826.3
First chunk1625 ms545 ms
TTFT1.6 s545 ms
Load time21.8 s9.5 s
Memory usage5.2 GB8.4 GB
Memory %71%7%
HW Fit Score Breakdown
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
Quality
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
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
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