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

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

Global Score

73 vs 46

Hardware Fit

100 vs 93

Quality Score

61 vs 26

Hardware

qwen2.5-coder-3b-i… gemma3:4b

MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4Cortex-A78AE

Cores106

RAM32 GB7 GB

GPUApple M4Integrated / Unknown

OSmacOS 26.3Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5-coder-3b-i… gemma3:4b

Tokens/sec52.314.9

First chunk285 ms2204 ms

TTFT285 ms2.2 s

Load timeN/A2.0 s

Memory usage1.6 GB2.6 GB

Memory %5%35%

HW Fit Score Breakdown

qwen2.5-coder-3b-instru…

Speed

50/50

TTFT

20/20

Memory

30/30

gemma3:4b

Speed

45/50

TTFT

19/20

Memory

29/30

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

gemma3:4b

Reasoning

11/20

Coding

11/20

Instruction

0/20

Structured

0/15

Math

4/15

Multilingual

0/10

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

View qwen2.5-coder-3b-i… details | View gemma3:4b 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