gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
94 vs 80
Hardware Fit
92 vs 60
Quality Score
95 vs 88
Hardware
gpt-oss:20b qwen3-coder:30b
MachineMacBook ProASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-12700K
Cores1420
RAM48 GB96 GB
GPUApple M4 ProParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 26.4.1Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b qwen3-coder:30b
Tokens/sec54.514.7
First chunk318 ms796 ms
TTFT2.9 s796 ms
Load time4.0 s0.2 s
Memory usage16.4 GB17.9 GB
Memory %34%19%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
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
Reasoning
17/20
Coding
19/20
Instruction
16/20
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest