microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

Global Score

64 vs 46

Hardware Fit

100 vs 61

Quality Score

48 vs 40

Hardware

microsoft/phi-4-mi… llama3.1:8b

MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4 ProCortex-A78AE

Cores146

RAM64 GB7 GB

GPUApple M4 ProIntegrated / Unknown

OSmacOS 15.7.4Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… llama3.1:8b

Tokens/sec90.37.8

First chunk198 ms1625 ms

TTFT198 ms1.6 s

Load timeN/A21.8 s

Memory usage2.0 GB5.2 GB

Memory %3%71%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

30/30

llama3.1:8b

Speed

26/50

TTFT

20/20

Memory

15/30

Quality

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

7/20

Instruction

7/20

Structured

7/15

Math

13/15

Multilingual

7/10

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

llama3.1:8b

Reasoning

12/20

Coding

10/20

Instruction

4/20

Structured

1/15

Math

4/15

Multilingual

9/10

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

View microsoft/phi-4-mi… details | View llama3.1:8b 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