gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jun 25, 2026 · Cortex-X925
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor
Global Score
92 vs 78
Hardware Fit
86 vs 86
Quality Score
95 vs 74
Hardware
gpt-oss:20b qwen3:8b
MachineNVIDIA NVIDIA_DGX_Spark—
CPUCortex-X925AMD Ryzen 9 3900X 12-Core Processor
Cores2024
RAM122 GB64 GB
GPUDevice 2e12NVIDIA GeForce RTX 4060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
gpt-oss:20b qwen3:8b
Tokens/sec60.748.5
First chunk542 ms202 ms
TTFT3.2 s4.3 s
Load time12.0 s4.2 s
Memory usage12.0 GB5.5 GB
Memory %10%9%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
30/30
qwen3:8b
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
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
qwen3:8b
Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak 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