starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score

35 vs 80

Hardware Fit

100 vs 100

Quality Score

7 vs 71

Hardware

starcoder2:3b gemma-3-4b-it-q4-k-m

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMac Pro

CPUCortex-A78AEIntel Core™ i5-10400

Cores612

RAM7 GB32 GB

GPUIntegrated / UnknownAMD Radeon RX 6700 XT

OSUbuntu 22.04.5 LTSmacOS 26.5.1

Archarm64x64

Power Modebalancedbalanced

Performance

starcoder2:3b gemma-3-4b-it-q4-k-m

Tokens/sec31.575.0

First chunk392 ms136 ms

TTFT392 ms136 ms

Load time4.8 s0.0 s

Memory usage1.8 GB0.8 GB

Memory %24%3%

HW Fit Score Breakdown

starcoder2:3b

Speed

50/50

TTFT

20/20

Memory

30/30

gemma-3-4b-it-q4-k-m

Speed

50/50

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

gemma-3-4b-it-q4-k-m

Reasoning

11/20

Coding

17/20

Instruction

14/20

Structured

14/15

Math

5/15

Multilingual

10/10

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

View starcoder2:3b details | View gemma-3-4b-it-q4-k-m 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