microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.8-27b-fable-distill-heretic-ara-i1

LM-STUDIO GGUF

qwen35 · 27B · IQ3_S

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score

62 vs 88

Hardware Fit

99 vs 98

Quality Score

46 vs 84

Hardware

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

MachineMacBook AirMicro-Star International Co., Ltd. MS-7E51

CPUApple M4AMD Ryzen 7 9700X 8-Core Processor

Cores1016

RAM32 GB31 GB

GPUApple M4NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics

OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

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

Tokens/sec40.348.8

First chunk289 ms18 ms

TTFT289 ms276 ms

Load timeN/AN/A

Memory usage2.0 GB11.7 GB

Memory %6%38%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3.8-27b-fable-disti…

Speed

50/50

TTFT

20/20

Memory

28/30

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-fable-disti…

Reasoning

15/20

Coding

18/20

Instruction

15/20

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-fable-… 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