gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
Global Score
87 vs 81
Hardware Fit
83 vs 100
Quality Score
88 vs 73
Hardware
gpt-oss:20b llama-3.1-8b-instr…
MachineMac miniASUS
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM24 GB31 GB
GPUApple M4Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Nobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
gpt-oss:20b llama-3.1-8b-instr…
Tokens/sec24.335.6
First chunk529 ms52 ms
TTFT4.5 s256 ms
Load time11.2 sN/A
Memory usage13.1 GB8.6 GB
Memory %55%28%
HW Fit Score Breakdown
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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