qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
82 vs 28
Hardware Fit
90 vs 66
Quality Score
79 vs 11
Hardware
qwen3:14b phi-1_5
MachineMicro-Star International Co., Ltd. MS-7C37LENOVO 20BUS00700
CPUAMD Ryzen 9 3900X 12-Core ProcessorIntel Core™ i5-5300U
Cores244
RAM64 GB16 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Intel(R) HD Graphics 5500
OSMicrosoft Windows 11 专业版 10.0.26200Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
qwen3:14b phi-1_5
Tokens/sec74.46.9
First chunk324 ms3040 ms
TTFT2.6 s3.0 s
Load time5.1 sN/A
Memory usage9.0 GB1.4 GB
Memory %14%9%
HW Fit Score Breakdown
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
Quality
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
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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