gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
33 vs 74
Hardware Fit
50 vs 99
Quality Score
25 vs 63
Hardware
gemma4:26b llama3.2:3b
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM24 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:26b llama3.2:3b
Tokens/sec20.021.1
First chunk941 ms1032 ms
TTFT30.0 s1.0 s
Load time0.2 s8.4 s
Memory usage20.3 GB2.4 GB
Memory %85%32%
HW Fit Score Breakdown
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
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
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
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