gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
88 vs 80
Hardware Fit
80 vs 77
Quality Score
91 vs 81
Hardware
gpt-oss-orchestrat… qwen3.6:35b-mlx
MachineMac miniMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM24 GB48 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss-orchestrat… qwen3.6:35b-mlx
Tokens/sec24.6129.8
First chunk525 ms77 ms
TTFT4.8 s30.0 s
Load time8.5 s1.8 s
Memory usage13.8 GB19.7 GB
Memory %58%41%
HW Fit Score Breakdown
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
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
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate 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