Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

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

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
82 vs 65
Hardware Fit
90 vs 87
Quality Score
79 vs 56

Hardware

qwen3:14b qwen2.5:1.5b
MachineMicro-Star International Co., Ltd. MS-7C37Shanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUAMD Ryzen 9 3900X 12-Core ProcessorZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores248
RAM64 GB30 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080ZX C-1190
OSMicrosoft Windows 11 专业版 10.0.26200Microsoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:14b qwen2.5:1.5b
Tokens/sec74.416.8
First chunk324 ms941 ms
TTFT2.6 s941 ms
Load time5.1 s0.2 s
Memory usage9.0 GB1.0 GB
Memory %14%3%

HW Fit Score Breakdown

qwen3:14b

Speed
50/50
TTFT
10/20
Memory
30/30

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
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

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3:14b details | View qwen2.5:1.5b details

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