microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score

64 vs 81

Hardware Fit

100 vs 64

Quality Score

48 vs 88

Hardware

microsoft/phi-4-mi… qwen3.8-27b-uncens…

MachineMac miniSystem manufacturer

CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor

Cores1416

RAM64 GB31 GB

GPUApple M4 ProNavi 44 [Radeon RX 9060 XT]

OSmacOS 15.7.4Ubuntu 26.04.1 LTS

Archarm64x64

Power Modebalancedperformance

Performance

microsoft/phi-4-mi… qwen3.8-27b-uncens…

Tokens/sec90.311.7

First chunk198 ms50 ms

TTFT198 ms1.1 s

Load timeN/AN/A

Memory usage2.0 GB15.8 GB

Memory %3%51%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3.8-27b-uncensored-…

Speed

19/50

TTFT

20/20

Memory

25/30

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

qwen3.8-27b-uncensored-…

Reasoning

17/20

Coding

19/20

Instruction

16/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View qwen3.8-27b-uncens… 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