phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 27, 2026 · AMD RYZEN AI MAX+ 395

Global Score

55 vs 83

Hardware Fit

100 vs 100

Quality Score

36 vs 76

Hardware

phi-3.5-mini-instr… glm-4.7-flash:latest

MachineMacBook AirAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM32 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedperformance

Performance

phi-3.5-mini-instr… glm-4.7-flash:latest

Tokens/sec43.458.0

First chunk359 ms268 ms

TTFT359 ms268 ms

Load timeN/A7.8 s

Memory usage2.0 GB37.7 GB

Memory %6%30%

HW Fit Score Breakdown

phi-3.5-mini-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

glm-4.7-flash:latest

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

glm-4.7-flash:latest

Reasoning

13/20

Coding

17/20

Instruction

11/20

Structured

15/15

Math

10/15

Multilingual

10/10

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

View phi-3.5-mini-instr… details | View glm-4.7-flash:latest 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