Back to leaderboard

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
35 vs 82
Hardware Fit
100 vs 90
Quality Score
7 vs 79

Hardware

starcoder2:3b qwen3:14b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicro-Star International Co., Ltd. MS-7C37
CPUCortex-A78AEAMD Ryzen 9 3900X 12-Core Processor
Cores624
RAM7 GB64 GB
GPUIntegrated / UnknownGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 专业版 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

starcoder2:3b qwen3:14b
Tokens/sec31.574.4
First chunk392 ms324 ms
TTFT392 ms2.6 s
Load time4.8 s5.1 s
Memory usage1.8 GB9.0 GB
Memory %24%14%

HW Fit Score Breakdown

starcoder2:3b

Speed
50/50
TTFT
20/20
Memory
30/30

qwen3:14b

Speed
50/50
TTFT
10/20
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

qwen3:14b

Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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