llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
google/gemma-4-26b-a4b-qat
LM-STUDIO GGUFgemma4 · 26B · Q4_0
Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
74 vs 93
Hardware Fit
99 vs 96
Quality Score
63 vs 92
Hardware
llama3.2:3b google/gemma-4-26b…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicro-Star International Co., Ltd. MS-7E51
CPUCortex-A78AEAMD Ryzen 7 9700X 8-Core Processor
Cores616
RAM7 GB31 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b google/gemma-4-26b…
Tokens/sec21.1109.7
First chunk1032 ms29 ms
TTFT1.0 s156 ms
Load time8.4 sN/A
Memory usage2.4 GB14.6 GB
Memory %32%47%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
google/gemma-4-26b-a4b-…
Speed
50/50
TTFT
20/20
Memory
26/30
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
google/gemma-4-26b-a4b-…
Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
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