Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score
90 vs 47
Hardware Fit
88 vs 53
Quality Score
91 vs 45

Hardware

openai/gpt-oss-20b qwen3:4b
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 Modeperformanceunknown

Performance

openai/gpt-oss-20b qwen3:4b
Tokens/sec58.711.3
First chunk6 msN/A
TTFT4.5 s9.2 s
Load timeN/A0.1 s
Memory usage11.9 GB7.2 GB
Memory %38%23%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen3:4b

Speed
17/50
TTFT
6/20
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

qwen3:4b

Reasoning
4/20
Coding
6/20
Instruction
8/20
Structured
6/15
Math
12/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View openai/gpt-oss-20b details | View qwen3:4b details

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