llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Mar 5, 2026 · AMD Ryzen 9 8945HS
qwen2.5-coder:3b
OLLAMA GGUFqwen2 · 3.1B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
62 vs 73
Hardware Fit
91 vs 100
Quality Score
50 vs 61
Hardware
llama3.2:1b qwen2.5-coder:3b
MachineASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UVNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 9 8945HSCortex-A78AE
Cores166
RAM15 GB7 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M GraphicsIntegrated / Unknown
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.2:1b qwen2.5-coder:3b
Tokens/sec170.221.3
First chunk142 ms969 ms
TTFT142 ms969 ms
Load time3.2 s6.6 s
Memory usage1.6 GB2.0 GB
Memory %11%27%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
21/30
qwen2.5-coder:3b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:1b
Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
qwen2.5-coder:3b
Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate 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