qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
ornith-1.5-35b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Aug 21, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
82 vs 85
Hardware Fit
90 vs 88
Quality Score
79 vs 84
Hardware
qwen3:14b ornith-1.5-35b
MachineMicro-Star International Co., Ltd. MS-7C37Micro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 9 3900X 12-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores2416
RAM64 GB31 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 专业版 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3:14b ornith-1.5-35b
Tokens/sec74.480.4
First chunk324 ms24 ms
TTFT2.6 s231 ms
Load time5.1 sN/A
Memory usage9.0 GB20.2 GB
Memory %14%65%
HW Fit Score Breakdown
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
ornith-1.5-35b
Speed
50/50
TTFT
20/20
Memory
18/30
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
ornith-1.5-35b
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
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