microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

ornith-1.5-9b_hybrid-imatrix

LM-STUDIO GGUF

qwen35 · F16

Not Rec.

Aug 23, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score

64 vs 66

Hardware Fit

100 vs 51

Quality Score

48 vs 73

Hardware

microsoft/phi-4-mi… ornith-1.5-9b_hybr…

MachineMac miniMicro-Star International Co., Ltd. MS-7C37

CPUApple M4 ProAMD Ryzen 9 3900X 12-Core Processor

Cores1424

RAM64 GB128 GB

GPUApple M4 ProIntel(R) Arc(TM) Pro B70 Graphics

OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… ornith-1.5-9b_hybr…

Tokens/sec90.35.4

First chunk198 ms39 ms

TTFT198 ms940 ms

Load timeN/AN/A

Memory usage2.0 GB10.7 GB

Memory %3%8%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

30/30

ornith-1.5-9b_hybrid-im…

Speed

5/50

TTFT

16/20

Memory

30/30

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

ornith-1.5-9b_hybrid-im…

Reasoning

14/20

Coding

14/20

Instruction

11/20

Structured

15/15

Math

9/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View ornith-1.5-9b_hybr… 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