phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Jun 26, 2026 · Cortex-A78AE

Global Score

38 vs 63

Hardware Fit

100 vs 100

Quality Score

12 vs 47

Hardware

phi-3-mini-128k-in… llama3.2:1b

MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4Cortex-A78AE

Cores106

RAM32 GB7 GB

GPUApple M4Integrated / Unknown

OSmacOS 26.3Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… llama3.2:1b

Tokens/sec44.040.2

First chunk384 ms1087 ms

TTFT385 ms1.1 s

Load timeN/A6.2 s

Memory usage2.0 GB1.4 GB

Memory %6%19%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

llama3.2:1b

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

llama3.2:1b

Reasoning

4/20

Coding

9/20

Instruction

14/20

Structured

13/15

Math

1/15

Multilingual

6/10

Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

View phi-3-mini-128k-in… details | View llama3.2:1b 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