phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

qwen3-0.6b

LM-STUDIO GGUF

qwen3 · 0.6B · Q4_K_M

Marginal

Mar 5, 2026 · Intel Core™ i5-5300U

Global Score

38 vs 40

Hardware Fit

100 vs 89

Quality Score

12 vs 19

Hardware

phi-3-mini-128k-in… qwen3-0.6b

MachineMacBook AirLENOVO 20BUS00700

CPUApple M4Intel Core™ i5-5300U

Cores104

RAM32 GB16 GB

GPUApple M4Intel(R) HD Graphics 5500

OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… qwen3-0.6b

Tokens/sec44.014.4

First chunk384 ms854 ms

TTFT385 ms854 ms

Load timeN/AN/A

Memory usage2.0 GB0.5 GB

Memory %6%3%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3-0.6b

Speed

43/50

TTFT

20/20

Memory

26/30

Quality

phi-3-mini-128k-instruct

Reasoning

3/20

Coding

2/20

Instruction

2/20

Structured

1/15

Math

2/15

Multilingual

2/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3-0.6b

Reasoning

5/20

Coding

1/20

Instruction

3/20

Structured

4/15

Math

0/15

Multilingual

6/10

Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Poor Multilingual: Adequate

View phi-3-mini-128k-in… details | View qwen3-0.6b 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