qwen2.5-coder:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Nov 13, 2026 · Intel Core™ i5-4590T
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
59 vs 79
Hardware Fit
100 vs 47
Quality Score
41 vs 93
Hardware
qwen2.5-coder:0.5b GPT-120B:120b
MachineFUJITSU ESPRIMO Q920HP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUIntel Core™ i5-4590TIntel Core™ i7-14700F
Cores428
RAM16 GB128 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterNVIDIA GeForce RTX 5080
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen2.5-coder:0.5b GPT-120B:120b
Tokens/sec43.718.2
First chunk290 ms1719 ms
TTFT290 ms3.9 s
Load time1.4 s50.9 s
Memory usage0.9 GB61.5 GB
Memory %6%48%
HW Fit Score Breakdown
qwen2.5-coder:0.5b
Speed
50/50
TTFT
20/20
Memory
30/30
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
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
GPT-120B:120b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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