qwen2.5-coder:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Nov 13, 2026 · Intel Core™ i5-4590T
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
59 vs 76
Hardware Fit
100 vs 92
Quality Score
41 vs 69
Hardware
qwen2.5-coder:0.5b gemma3:4b
MachineFUJITSU ESPRIMO Q920NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-4590TCortex-A78AE
Cores46
RAM16 GB7 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterIntegrated / Unknown
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5-coder:0.5b gemma3:4b
Tokens/sec43.715.0
First chunk290 ms2380 ms
TTFT290 ms2.4 s
Load time1.4 s13.6 s
Memory usage0.9 GB2.6 GB
Memory %6%35%
HW Fit Score Breakdown
qwen2.5-coder:0.5b
Speed
50/50
TTFT
20/20
Memory
30/30
gemma3:4b
Speed
45/50
TTFT
18/20
Memory
29/30
Quality
qwen2.5-coder:0.5b
Reasoning
7/20
Coding
8/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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