Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Oct 20, 2026 · Apple M1 Pro

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score
83 vs 92
Hardware Fit
75 vs 95
Quality Score
87 vs 90

Hardware

openai/gpt-oss-20b qwen/qwen3-vl-30b
MachineMacBook ProASUS
CPUApple M1 ProAMD Ryzen 5 5500
Cores1012
RAM32 GB31 GB
GPUApple M1 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 15.6.1Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

openai/gpt-oss-20b qwen/qwen3-vl-30b
Tokens/sec43.224.8
First chunk46 ms11 ms
TTFT30.0 s735 ms
Load timeN/A11.7 s
Memory usage15.8 GB0.6 GB
Memory %49%2%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
25/30

qwen/qwen3-vl-30b

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

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View openai/gpt-oss-20b details | View qwen/qwen3-vl-30b 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