qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
82 vs 13
Hardware Fit
90 vs 41
Quality Score
79 vs 1
Hardware
qwen3:14b qwen3.5:2b
MachineMicro-Star International Co., Ltd. MS-7C37LENOVO 20L7CTO1WW
CPUAMD Ryzen 9 3900X 12-Core ProcessorIntel Core™ i5-8350U
Cores248
RAM64 GB23 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 专业版 10.0.26200Fedora Linux 43
Archx64x64
Power Modebalancedlow-power
Performance
qwen3:14b qwen3.5:2b
Tokens/sec74.44.5
First chunk324 ms1413 ms
TTFT2.6 s31.1 s
Load time5.1 s7.1 s
Memory usage9.0 GB3.8 GB
Memory %14%16%
HW Fit Score Breakdown
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
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
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
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