deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
64 vs 90
Hardware Fit
98 vs 79
Quality Score
49 vs 94
Hardware
deepscaler:1.5b GPT-20B:20b
MachineMicrosoft WSLHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUAMD Ryzen 5 5500AMD Ryzen 9 9955HX3D 16-Core Processor
Cores1232
RAM8 GB31 GB
GPUIntegrated / UnknownAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeunknownbalanced
Performance
deepscaler:1.5b GPT-20B:20b
Tokens/sec104.636.6
First chunk849 ms722 ms
TTFT850 ms4.7 s
Load time10.5 s0.3 s
Memory usage3.0 GB13.1 GB
Memory %40%42%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
Quality
deepscaler:1.5b
Reasoning
10/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
11/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
17/20
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