gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
88 vs 83
Hardware Fit
80 vs 64
Quality Score
91 vs 91
Hardware
gpt-oss-orchestrat… gpt-oss:120b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM24 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gpt-oss-orchestrat… gpt-oss:120b
Tokens/sec24.628.6
First chunk525 ms422 ms
TTFT4.8 s2.5 s
Load time8.5 s9.9 s
Memory usage13.8 GB60.1 GB
Memory %58%49%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
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
gpt-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
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