llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
Global Score
74 vs 33
Hardware Fit
99 vs 50
Quality Score
63 vs 25
Hardware
llama3.2:3b gemma4:26b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMac mini
CPUCortex-A78AEApple M4
Cores610
RAM7 GB24 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 22.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:3b gemma4:26b
Tokens/sec21.120.0
First chunk1032 ms941 ms
TTFT1.0 s30.0 s
Load time8.4 s0.2 s
Memory usage2.4 GB20.3 GB
Memory %32%85%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
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
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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