gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · Intel Core™ Ultra 9 285K
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
95 vs 61
Hardware Fit
98 vs 85
Quality Score
94 vs 51
Hardware
gpt-oss:20b qwen3:0.6b
MachineASUSLENOVO 20L7CTO1WW
CPUIntel Core™ Ultra 9 285KIntel Core™ i5-8350U
Cores248
RAM47 GB23 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsKaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Pro 10.0.26200Fedora Linux 43
Archx64x64
Power Modebalancedlow-power
Performance
gpt-oss:20b qwen3:0.6b
Tokens/sec239.927.0
First chunk180 ms597 ms
TTFT616 ms8.7 s
Load time4.3 s1.8 s
Memory usage13.9 GB0.9 GB
Memory %29%4%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
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