gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
microllm-10m:latest
OLLAMA GGUFllama · 10.00M · F16
Jun 28, 2026 · Apple M4 Pro
Global Score
88 vs 33
Hardware Fit
80 vs 100
Quality Score
91 vs 4
Hardware
gpt-oss-orchestrat… microllm-10m:latest
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… microllm-10m:latest
Tokens/sec24.61544.8
First chunk525 ms12 ms
TTFT4.8 s12 ms
Load time8.5 s0.0 s
Memory usage13.8 GB0.0 GB
Memory %58%0%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
microllm-10m:latest
Speed
50/50
TTFT
20/20
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
microllm-10m:latest
Reasoning
0/20
Coding
0/20
Instruction
4/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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