qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
13 vs 87
Hardware Fit
41 vs 81
Quality Score
1 vs 90
Hardware
qwen3.5:2b GPT-20B:20b
MachineLENOVO 20L7CTO1WWHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Core™ i5-8350UAMD Ryzen 9 9955HX3D 16-Core Processor
Cores832
RAM23 GB31 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSFedora Linux 43Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3.5:2b GPT-20B:20b
Tokens/sec4.536.9
First chunk1413 ms902 ms
TTFT31.1 s4.2 s
Load time7.1 s19.5 s
Memory usage3.8 GB13.1 GB
Memory %16%42%
HW Fit Score Breakdown
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
GPT-20B:20b
Speed
47/50
TTFT
7/20
Memory
27/30
Quality
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
GPT-20B:20b
Reasoning
19/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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