llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
46 vs 90
Hardware Fit
61 vs 88
Quality Score
40 vs 91
Hardware
llama3.1:8b openai/gpt-oss-20b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEAMD Ryzen 5 5500
Cores612
RAM7 GB31 GB
GPUIntegrated / UnknownNavi 44 [Radeon RX 9060 XT]
OSUbuntu 22.04.5 LTSNobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
llama3.1:8b openai/gpt-oss-20b
Tokens/sec7.858.7
First chunk1625 ms6 ms
TTFT1.6 s4.5 s
Load time21.8 sN/A
Memory usage5.2 GB11.9 GB
Memory %71%38%
HW Fit Score Breakdown
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
Quality
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
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
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