Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

Global Score
83 vs 90
Hardware Fit
80 vs 89
Quality Score
84 vs 90

Hardware

openai/gpt-oss-20b qwen3-coder:30b-a3…
MachineMacBook ProMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUApple M5 MaxIntel Core™ Ultra 9 285HX
Cores1824
RAM64 GB63 GB
GPUApple M5 MaxIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSmacOS 27.0Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

openai/gpt-oss-20b qwen3-coder:30b-a3…
Tokens/sec131.743.1
First chunk7 ms957 ms
TTFT30.0 s957 ms
Load timeN/A52.0 s
Memory usage15.8 GB33.6 GB
Memory %25%53%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen3-coder:30b-a3b-q8_0

Speed
46/50
TTFT
19/20
Memory
24/30

Quality

openai/gpt-oss-20b

Reasoning
18/20
Coding
13/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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