gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
88 vs 80
Hardware Fit
80 vs 100
Quality Score
91 vs 71
Hardware
gpt-oss-orchestrat… gemma3:4b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss-orchestrat… gemma3:4b
Tokens/sec24.634.6
First chunk525 msN/A
TTFT4.8 s303 ms
Load time8.5 s1.2 s
Memory usage13.8 GB4.6 GB
Memory %58%14%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
gemma3:4b
Speed
40/50
TTFT
30/20
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
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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