Back to leaderboard

gpt-oss-orchestrator:latest

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 19, 2026 · Apple M4

phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
88 vs 55
Hardware Fit
80 vs 100
Quality Score
91 vs 36

Hardware

gpt-oss-orchestrat… phi-3.5-mini-instr…
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… phi-3.5-mini-instr…
Tokens/sec24.643.4
First chunk525 ms359 ms
TTFT4.8 s359 ms
Load time8.5 sN/A
Memory usage13.8 GB2.0 GB
Memory %58%6%

HW Fit Score Breakdown

gpt-oss-orchestrator:la…

Speed
49/50
TTFT
10/20
Memory
21/30

phi-3.5-mini-instruct

Speed
50/50
TTFT
20/20
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

phi-3.5-mini-instruct

Reasoning
11/20
Coding
4/20
Instruction
7/20
Structured
1/15
Math
7/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate
View gpt-oss-orchestrat… details | View phi-3.5-mini-instr… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest