gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
88 vs 84
Hardware Fit
80 vs 69
Quality Score
91 vs 91
Hardware
gpt-oss-orchestrat… gptoss · 20.9B · M…
MachineMac miniMac Pro
CPUApple M4Intel Core™ i5-10400
Cores1012
RAM24 GB32 GB
GPUApple M4AMD Radeon RX 6700 XT
OSmacOS 26.3macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss-orchestrat… gptoss · 20.9B · M…
Tokens/sec24.617.5
First chunk525 ms643 ms
TTFT4.8 s7.7 s
Load time8.5 s0.0 s
Memory usage13.8 GB0.8 GB
Memory %58%3%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
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
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