GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
94 vs 80
Hardware Fit
96 vs 60
Quality Score
93 vs 88
Hardware
GPT-20B:20b qwen3-coder:30b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUS
CPUIntel Core™ i7-14700FIntel Gen Intel® Core™ i7-12700K
Cores2820
RAM64 GB96 GB
GPUNVIDIA GeForce RTX 5080Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-20B:20b qwen3-coder:30b
Tokens/sec181.014.7
First chunk596 ms796 ms
TTFT1.3 s796 ms
Load time10.0 s0.2 s
Memory usage11.9 GB17.9 GB
Memory %19%19%
HW Fit Score Breakdown
GPT-20B:20b
Speed
50/50
TTFT
16/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
Quality
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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