Back to leaderboard

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 4, 2026 · Apple M4

Global Score
38 vs 94
Hardware Fit
100 vs 100
Quality Score
12 vs 92

Hardware

phi-3-mini-128k-in… openai/gpt-oss-20b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… openai/gpt-oss-20b
Tokens/sec44.040.7
First chunk384 ms824 ms
TTFT385 ms1.3 s
Load timeN/AN/A
Memory usage2.0 GB11.3 GB
Memory %6%35%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

Speed
50/50
TTFT
20/20
Memory
30/30

openai/gpt-oss-20b

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

phi-3-mini-128k-instruct

Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

openai/gpt-oss-20b

Reasoning
20/20
Coding
18/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View phi-3-mini-128k-in… details | View openai/gpt-oss-20b 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