starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
35 vs 85
Hardware Fit
100 vs 100
Quality Score
7 vs 79
Hardware
starcoder2:3b phi4:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUCortex-A78AEIntel Core™ i5-14400F
Cores616
RAM7 GB32 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5060 Ti
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
starcoder2:3b phi4:latest
Tokens/sec31.538.3
First chunk392 ms72 ms
TTFT392 ms72 ms
Load time4.8 s6.2 s
Memory usage1.8 GB9.1 GB
Memory %24%29%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
phi4:latest
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
phi4:latest
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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