starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
nemotron-3.5-lightning:latest
OLLAMA GGUFnemotron_h_moe · 32.9B · Q4_K_M
Aug 17, 2026 · Cortex-X925
Global Score
35 vs 87
Hardware Fit
100 vs 80
Quality Score
7 vs 90
Hardware
starcoder2:3b nemotron-3.5-light…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUSTeK COMPUTER INC. GX10
CPUCortex-A78AECortex-X925
Cores620
RAM7 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
starcoder2:3b nemotron-3.5-light…
Tokens/sec31.584.1
First chunk392 ms371 ms
TTFT392 ms30.0 s
Load time4.8 s0.3 s
Memory usage1.8 GB24.9 GB
Memory %24%20%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
nemotron-3.5-lightning:…
Speed
50/50
TTFT
0/20
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
nemotron-3.5-lightning:…
Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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