starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score

35 vs 64

Hardware Fit

100 vs 69

Quality Score

7 vs 62

Hardware

starcoder2:3b qwen3.5:4b

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20U30029MB

CPUCortex-A78AEIntel Core™ i5-10210U

Cores68

RAM7 GB15 GB

GPUIntegrated / UnknownCometLake-U GT2 [UHD Graphics]

OSUbuntu 22.04.5 LTSPop 24.04 LTS

Archarm64x64

Power Modebalancedperformance

Performance

starcoder2:3b qwen3.5:4b

Tokens/sec31.57.4

First chunk392 ms1815 ms

TTFT392 ms1.8 s

Load time4.8 s10.9 s

Memory usage1.8 GB3.5 GB

Memory %24%23%

HW Fit Score Breakdown

starcoder2:3b

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3.5:4b

Speed

19/50

TTFT

20/20

Memory

30/30

Quality

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

qwen3.5:4b

Reasoning

15/20

Coding

14/20

Instruction

6/20

Structured

12/15

Math

6/15

Multilingual

9/10

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

View starcoder2:3b details | View qwen3.5:4b 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