qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score

65 vs 35

Hardware Fit

73 vs 100

Quality Score

62 vs 7

Hardware

qwen3.5:4b starcoder2:3b

MachineAZW GTR ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUAMD RYZEN AI MAX+ 395Cortex-A78AE

Cores326

RAM125 GB7 GB

GPUAMD Radeon 8060SIntegrated / Unknown

OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS

Archx64arm64

Power Modelow-powerbalanced

Performance

qwen3.5:4b starcoder2:3b

Tokens/sec45.731.5

First chunk180 ms392 ms

TTFT30.0 s392 ms

Load time5.3 s4.8 s

Memory usage16.2 GB1.8 GB

Memory %13%24%

HW Fit Score Breakdown

qwen3.5:4b

Speed

43/50

TTFT

0/20

Memory

30/30

starcoder2:3b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

qwen3.5:4b

Reasoning

17/20

Coding

1/20

Instruction

13/20

Structured

8/15

Math

13/15

Multilingual

10/10

Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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 qwen3.5:4b 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