Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score
89 vs 90
Hardware Fit
95 vs 88
Quality Score
87 vs 91

Hardware

qwen/qwen3-8b openai/gpt-oss-20b
MachineMac miniASUS
CPUApple M4 ProAMD Ryzen 5 5500
Cores1412
RAM64 GB31 GB
GPUApple M4 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 15.7.4Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

qwen/qwen3-8b openai/gpt-oss-20b
Tokens/sec33.458.7
First chunk257 ms6 ms
TTFT257 ms4.5 s
Load timeN/AN/A
Memory usage4.3 GB11.9 GB
Memory %7%38%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

openai/gpt-oss-20b

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

Quality

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong 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
View qwen/qwen3-8b details | View openai/gpt-oss-20b 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