Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

smollm2:135m

OLLAMA GGUF

llama · 134.52M · F16

Marginal

Mar 2, 2026 · Apple M4

Global Score
90 vs 41
Hardware Fit
88 vs 100
Quality Score
91 vs 15

Hardware

openai/gpt-oss-20b smollm2:135m
MachineASUSMacBook Air
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4
OSNobara Linux 43macOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

openai/gpt-oss-20b smollm2:135m
Tokens/sec58.7241.0
First chunk6 msN/A
TTFT4.5 s39 ms
Load timeN/A0.4 s
Memory usage11.9 GB0.6 GB
Memory %38%2%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
10/20
Memory
28/30

smollm2:135m

Speed
40/50
TTFT
30/20
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

smollm2:135m

Reasoning
4/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest