qwen3:4b
OLLAMA GGUFqwen3 · 4.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
32 vs 94
Hardware Fit
98 vs 91
Quality Score
4 vs 95
Hardware
qwen3:4b gpt-oss:20b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUCortex-A78AEAMD RYZEN AI MAX+ 395
Cores632
RAM7 GB64 GB
GPUIntegrated / UnknownAMD Radeon(TM) 8060S Graphics
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro for Workstations 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3:4b gpt-oss:20b
Tokens/sec17.948.0
First chunk950 ms357 ms
TTFT950 ms2.3 s
Load time9.7 s0.2 s
Memory usage3.0 GB16.4 GB
Memory %40%26%
HW Fit Score Breakdown
qwen3:4b
Speed
50/50
TTFT
20/20
Memory
28/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
qwen3:4b
Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
gpt-oss:20b
Reasoning
19/20
Coding
19/20
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