openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
qwen3-coder-30b-a3b-instruct-mlx
LM-STUDIO MLXqwen3_moe · 30B · 4bit
Oct 20, 2026 · Apple M1 Pro
Global Score
91 vs 87
Hardware Fit
90 vs 85
Quality Score
91 vs 88
Hardware
openai/gpt-oss-20b qwen3-coder-30b-a3…
MachineMacBook ProMacBook Pro
CPUApple M3 MaxApple M1 Pro
Cores1610
RAM128 GB32 GB
GPUApple M3 MaxApple M1 Pro
OSmacOS 27.2macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b qwen3-coder-30b-a3…
Tokens/sec95.145.7
First chunk3 ms17 ms
TTFT2.5 s390 ms
Load time9.2 sN/A
Memory usage0.0 GB22.4 GB
Memory %0%70%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
qwen3-coder-30b-a3b-ins…
Speed
50/50
TTFT
20/20
Memory
15/30
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: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder-30b-a3b-ins…
Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest