Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Sep 29, 2026 · Apple M5 Max

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

Global Score
83 vs 89
Hardware Fit
80 vs 95
Quality Score
84 vs 87

Hardware

openai/gpt-oss-20b qwen/qwen3-8b
MachineMacBook ProMac mini
CPUApple M5 MaxApple M4 Pro
Cores1814
RAM128 GB64 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 26.6.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

openai/gpt-oss-20b qwen/qwen3-8b
Tokens/sec138.433.4
First chunk3 ms257 ms
TTFT30.0 s257 ms
Load time6.8 sN/A
Memory usage0.5 GB4.3 GB
Memory %0%7%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen/qwen3-8b

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

Quality

openai/gpt-oss-20b

Reasoning
18/20
Coding
12/20
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/qwen3-8b

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
View openai/gpt-oss-20b details | View qwen/qwen3-8b 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