gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
88 vs 89
Hardware Fit
80 vs 92
Quality Score
91 vs 88
Hardware
gpt-oss-orchestrat… qwen3-coder:30b
MachineMac miniGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M4Intel Core™ i5-14400F
Cores1016
RAM24 GB32 GB
GPUApple M4NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss-orchestrat… qwen3-coder:30b
Tokens/sec24.657.0
First chunk525 ms194 ms
TTFT4.8 s194 ms
Load time8.5 s13.8 s
Memory usage13.8 GB17.9 GB
Memory %58%56%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
22/30
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
16/20
Coding
19/20
Instruction
17/20
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