gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
88 vs 88
Hardware Fit
80 vs 86
Quality Score
91 vs 89
Hardware
gpt-oss-orchestrat… gemma4:12b-it-qat
MachineMac miniMac mini
CPUApple M4Apple M4 Pro
Cores1012
RAM24 GB24 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss-orchestrat… gemma4:12b-it-qat
Tokens/sec24.630.0
First chunk525 ms686 ms
TTFT4.8 s7.1 s
Load time8.5 s5.4 s
Memory usage13.8 GB7.1 GB
Memory %58%30%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
gpt-oss-orchestrator:la…
Reasoning
19/20
Coding
19/20
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
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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