qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
82 vs 75
Hardware Fit
90 vs 50
Quality Score
79 vs 86
Hardware
qwen3:14b qwen2.5:72b
MachineMicro-Star International Co., Ltd. MS-7C37NVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 9 3900X 12-Core ProcessorCortex-X925
Cores2420
RAM64 GB122 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Device 2e12
OSMicrosoft Windows 11 专业版 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
qwen3:14b qwen2.5:72b
Tokens/sec74.44.4
First chunk324 ms529 ms
TTFT2.6 s529 ms
Load time5.1 s49.7 s
Memory usage9.0 GB54.0 GB
Memory %14%44%
HW Fit Score Breakdown
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
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
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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