qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score

47 vs 35

Hardware Fit

53 vs 100

Quality Score

45 vs 7

Hardware

qwen3:4b starcoder2:3b

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 Modeunknownbalanced

Performance

qwen3:4b starcoder2:3b

Tokens/sec11.331.5

First chunkN/A392 ms

TTFT9.2 s392 ms

Load time0.1 s4.8 s

Memory usage7.2 GB1.8 GB

Memory %23%24%

HW Fit Score Breakdown

qwen3:4b

Speed

17/50

TTFT

6/20

Memory

30/30

starcoder2:3b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

qwen3:4b

Reasoning

4/20

Coding

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

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

starcoder2:3b

Reasoning

0/20

Coding

3/20

Instruction

1/20

Structured

0/15

Math

1/15

Multilingual

2/10

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

View qwen3:4b details | View starcoder2:3b 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