microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score

62 vs 84

Hardware Fit

99 vs 81

Quality Score

46 vs 85

Hardware

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

MachineMacBook AirGigabyte Technology Co., Ltd. X570 AORUS PRO

CPUApple M4AMD Ryzen 5 5600X 6-Core Processor

Cores1012

RAM32 GB32 GB

GPUApple M4NVIDIA GeForce RTX 5070 Ti

OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

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

Tokens/sec40.318.3

First chunk289 ms9 ms

TTFT289 ms522 ms

Load timeN/A7.7 s

Memory usage2.0 GB14.9 GB

Memory %6%47%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3.8-27b-uncensored-…

Speed

35/50

TTFT

20/20

Memory

26/30

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

qwen3.8-27b-uncensored-…

Reasoning

16/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

10/15

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