phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score

55 vs 81

Hardware Fit

100 vs 100

Quality Score

36 vs 73

Hardware

phi-3.5-mini-instr… llama-3.1-8b-instr…

MachineMacBook AirASUS

CPUApple M4AMD Ryzen 5 5500

Cores1012

RAM32 GB31 GB

GPUApple M4Navi 44 [Radeon RX 9060 XT]

OSmacOS 26.3Nobara Linux 43

Archarm64x64

Power Modebalancedperformance

Performance

phi-3.5-mini-instr… llama-3.1-8b-instr…

Tokens/sec43.435.6

First chunk359 ms52 ms

TTFT359 ms256 ms

Load timeN/AN/A

Memory usage2.0 GB8.6 GB

Memory %6%28%

HW Fit Score Breakdown

phi-3.5-mini-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

llama-3.1-8b-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

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

llama-3.1-8b-instruct

Reasoning

13/20

Coding

17/20

Instruction

13/20

Structured

15/15

Math

5/15

Multilingual

10/10

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

View phi-3.5-mini-instr… details | View llama-3.1-8b-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