phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score

38 vs 93

Hardware Fit

100 vs 91

Quality Score

12 vs 94

Hardware

phi-3-mini-128k-in… GPT-20B:20b

MachineMacBook AirHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML

CPUApple M4NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Cores1020

RAM32 GB55 GB

GPUApple M4NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU

OSmacOS 26.3Microsoft Windows 11 Pro 10.0.28000

Archarm64arm64

Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… GPT-20B:20b

Tokens/sec44.057.8

First chunk384 ms203 ms

TTFT385 ms3.0 s

Load timeN/A19.2 s

Memory usage2.0 GB12.0 GB

Memory %6%22%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

GPT-20B:20b

Speed

50/50

TTFT

11/20

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

GPT-20B:20b

Reasoning

19/20

Coding

17/20

Instruction

18/20

Structured

15/15

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 GPT-20B: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