GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen2.5-coder:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
94 vs 86
Hardware Fit
96 vs 100
Quality Score
93 vs 80
Hardware
GPT-20B:20b qwen2.5-coder:14b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Core™ i7-14700FIntel Core™ i5-14400F
Cores2816
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-20B:20b qwen2.5-coder:14b
Tokens/sec181.038.3
First chunk596 ms78 ms
TTFT1.3 s78 ms
Load time10.0 s6.3 s
Memory usage11.9 GB8.8 GB
Memory %19%28%
HW Fit Score Breakdown
GPT-20B:20b
Speed
50/50
TTFT
16/20
Memory
30/30
qwen2.5-coder:14b
Speed
50/50
TTFT
20/20
Memory
30/30
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
qwen2.5-coder:14b
Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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