gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
deepseek-r1:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
88 vs 22
Hardware Fit
80 vs 50
Quality Score
91 vs 10
Hardware
gpt-oss-orchestrat… deepseek-r1:14b
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… deepseek-r1:14b
Tokens/sec24.611.4
First chunk525 msN/A
TTFT4.8 s30.0 s
Load time8.5 s1.0 s
Memory usage13.8 GB16.5 GB
Memory %58%52%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
deepseek-r1:14b
Speed
20/50
TTFT
0/20
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
deepseek-r1:14b
Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
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