microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score

62 vs 81

Hardware Fit

99 vs 89

Quality Score

46 vs 77

Hardware

microsoft/phi-4-mi… glm-4.7-flash:q4_K_M

MachineMacBook AirASUS

CPUApple M4Intel Core™ i5-14600KF

Cores1020

RAM32 GB32 GB

GPUApple M4NVIDIA GeForce RTX 4070 Ti SUPER

OSmacOS 26.3Microsoft Windows 11 Famille 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… glm-4.7-flash:q4_K_M

Tokens/sec40.335.1

First chunk289 ms440 ms

TTFT289 ms440 ms

Load timeN/A11.6 s

Memory usage2.0 GB18.4 GB

Memory %6%58%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

glm-4.7-flash:q4_K_M

Speed

49/50

TTFT

20/20

Memory

20/30

Quality

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

6/20

Instruction

7/20

Structured

7/15

Math

12/15

Multilingual

7/10

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

glm-4.7-flash:q4_K_M

Reasoning

13/20

Coding

17/20

Instruction

12/20

Structured

15/15

Math

10/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View glm-4.7-flash:q4_K_M 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