qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Mar 2, 2026 · Apple M4
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
70 vs 46
Hardware Fit
100 vs 93
Quality Score
57 vs 26
Hardware
qwen2.5:1.5b gemma3:4b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen2.5:1.5b gemma3:4b
Tokens/sec84.114.9
First chunkN/A2204 ms
TTFT119 ms2.2 s
Load time0.5 s2.0 s
Memory usage2.6 GB2.6 GB
Memory %8%35%
HW Fit Score Breakdown
qwen2.5:1.5b
Speed
40/50
TTFT
30/20
Memory
30/30
gemma3:4b
Speed
45/50
TTFT
19/20
Memory
29/30
Quality
qwen2.5:1.5b
Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
6/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma3:4b
Reasoning
11/20
Coding
11/20
Instruction
0/20
Structured
0/15
Math
4/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak 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