GPT-OSS-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
93 vs 83
Hardware Fit
92 vs 64
Quality Score
93 vs 91
Hardware
GPT-OSS-20B:20b gpt-oss:120b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i7-14700FCortex-X925
Cores2820
RAM128 GB122 GB
GPUNVIDIA GeForce RTX 5080Device 2e12
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 24.04.5 LTS
Archx64arm64
Power Modebalancedperformance
Performance
GPT-OSS-20B:20b gpt-oss:120b
Tokens/sec178.628.6
First chunk695 ms422 ms
TTFT1.4 s2.5 s
Load time31.2 s9.9 s
Memory usage11.9 GB60.1 GB
Memory %9%49%
HW Fit Score Breakdown
GPT-OSS-20B:20b
Speed
50/50
TTFT
12/20
Memory
30/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
Quality
GPT-OSS-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
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