gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H
Global Score
87 vs 83
Hardware Fit
79 vs 100
Quality Score
90 vs 75
Hardware
gpt-oss:20b qwen3:8b
MachineMac miniMicro-Star International Co., Ltd. Stealth GS77 12UH
CPUApple M4Intel Gen Intel® Core™ i9-12900H
Cores1020
RAM24 GB32 GB
GPUApple M4Intel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b qwen3:8b
Tokens/sec26.454.0
First chunk505 ms68 ms
TTFT6.7 s68 ms
Load time10.5 s6.1 s
Memory usage13.1 GB5.8 GB
Memory %55%18%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
23/30
qwen3:8b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:8b
Reasoning
15/20
Coding
15/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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