gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
88 vs 80
Hardware Fit
80 vs 60
Quality Score
91 vs 88
Hardware
gpt-oss-orchestrat… qwen3-coder:30b
MachineMac miniASUS
CPUApple M4Intel Gen Intel® Core™ i7-12700K
Cores1020
RAM24 GB96 GB
GPUApple M4Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 26.3Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss-orchestrat… qwen3-coder:30b
Tokens/sec24.614.7
First chunk525 ms796 ms
TTFT4.8 s796 ms
Load time8.5 s0.2 s
Memory usage13.8 GB17.9 GB
Memory %58%19%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
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
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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