microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score

62 vs 84

Hardware Fit

99 vs 79

Quality Score

46 vs 86

Hardware

microsoft/phi-4-mi… qwen3.6-35b-a3b-cl…

MachineMacBook AirASUS

CPUApple M4AMD Ryzen 7 7800X3D 8-Core Processor

Cores1016

RAM32 GB31 GB

GPUApple M4NVIDIA GeForce RTX 4090, Raphael

OSmacOS 26.3cachyos rolling

Archarm64x64

Power Modebalancedperformance

Performance

microsoft/phi-4-mi… qwen3.6-35b-a3b-cl…

Tokens/sec40.3147.6

First chunk289 ms3 ms

TTFT289 ms164 ms

Load timeN/AN/A

Memory usage2.0 GB25.1 GB

Memory %6%82%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3.6-35b-a3b-claude-…

Speed

50/50

TTFT

20/20

Memory

9/30

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

qwen3.6-35b-a3b-claude-…

Reasoning

18/20

Coding

17/20

Instruction

14/20

Structured

14/15

Math

13/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View qwen3.6-35b-a3b-cl… 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