openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
90 vs 81
Hardware Fit
88 vs 100
Quality Score
91 vs 73
Hardware
openai/gpt-oss-20b llama3.1:8b
MachineASUSGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD Ryzen 5 5500Intel Core™ i5-14400F
Cores1216
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 5060 Ti
OSNobara Linux 43Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
openai/gpt-oss-20b llama3.1:8b
Tokens/sec58.770.2
First chunk6 ms58 ms
TTFT4.5 s58 ms
Load timeN/A4.1 s
Memory usage11.9 GB4.9 GB
Memory %38%15%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
llama3.1:8b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
15/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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