llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
Global Score
74 vs 87
Hardware Fit
99 vs 75
Quality Score
63 vs 92
Hardware
llama3.2:3b gemma4:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicro-Star International Co., Ltd. MS-7E47
CPUCortex-A78AEAMD Ryzen 9 9950X 16-Core Processor
Cores632
RAM7 GB125 GB
GPUIntegrated / UnknownAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b gemma4:latest
Tokens/sec21.142.4
First chunk1032 ms472 ms
TTFT1.0 s3.8 s
Load time8.4 s0.3 s
Memory usage2.4 GB12.3 GB
Memory %32%10%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
gemma4:latest
Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
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