starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
lmstudio-community/gemma-4-e4b-it-qat
LM-STUDIO GGUFgemma4 · Q4_0
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
35 vs 77
Hardware Fit
100 vs 68
Quality Score
7 vs 81
Hardware
starcoder2:3b lmstudio-community…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperDocker Container
CPUCortex-A78AEIntel Gen Intel® Core™ i9-11900H
Cores616
RAM7 GB15 GB
GPUIntegrated / UnknownTigerLake-H GT1 [UHD Graphics]
OSUbuntu 22.04.5 LTSUbuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
starcoder2:3b lmstudio-community…
Tokens/sec31.511.4
First chunk392 ms28 ms
TTFT392 ms2.2 s
Load time4.8 s6.8 s
Memory usage1.8 GB0.6 GB
Memory %24%4%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
lmstudio-community/gemm…
Speed
21/50
TTFT
17/20
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
lmstudio-community/gemm…
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest