qwen2.5-coder-3b-instruct-mlx

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score

73 vs 65

Hardware Fit

100 vs 96

Quality Score

61 vs 51

Hardware

qwen2.5-coder-3b-i… qwen3-4b-qwen3.6-p…

MachineMacBook AirMac Studio

CPUApple M4Apple M2 Max

Cores1012

RAM32 GB96 GB

GPUApple M4Apple M2 Max

OSmacOS 26.3macOS 26.1

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5-coder-3b-i… qwen3-4b-qwen3.6-p…

Tokens/sec52.399.6

First chunk285 ms18 ms

TTFT285 ms1.6 s

Load timeN/A4.8 s

Memory usage1.6 GB0.3 GB

Memory %5%0%

HW Fit Score Breakdown

qwen2.5-coder-3b-instru…

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3-4b-qwen3.6-plus-r…

Speed

50/50

TTFT

16/20

Memory

30/30

Quality

qwen2.5-coder-3b-instru…

Reasoning

7/20

Coding

14/20

Instruction

13/20

Structured

14/15

Math

4/15

Multilingual

9/10

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

qwen3-4b-qwen3.6-plus-r…

Reasoning

8/20

Coding

4/20

Instruction

14/20

Structured

9/15

Math

8/15

Multilingual

8/10

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

View qwen2.5-coder-3b-i… details | View qwen3-4b-qwen3.6-p… 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