qwen3:14b

qwen3 · 14.8B · Q4_K_M

THINKING MODEL

Micro-Star International Co., Ltd. MS-7C37 (AMD Ryzen 9 3900X 12-Core Processor)

64 GB · Microsoft Windows 11 专业版 10.0.26200

Tested on June 13, 2026 · Submitted by hui.fang

Top 20% Compare

Global Score

82 /100

Excellent

Hardware Fit

90/100

Quality

79/100

Get this model

🦙

Ollama

ollama pull qwen3:14b

View on Ollama Library

ollama.com/library/qwen3

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Micro-Star International Co., Ltd. MS-7C37
CPU: AMD Ryzen 9 3900X 12-Core Processor
Cores: 24 total (24 perf)
Frequency: 3.8 GHz
RAM: 64 GB DDR4
GPU: GameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OS: Microsoft Windows 11 专业版 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 74.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 324 ms
Time to first token How fast the model starts responding — lower is better: 2.6 s
Load time Time to load the model into memory before inference: 5.1 s
Memory usage RAM consumed during inference — percentage of total system memory: 9.0 GB (14%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~946

Score breakdown

Speed

50/50

Time to first token

10/20

Memory

30/30

Quality

Reasoning

18/20

Coding

11/20

Instruction following

17/20

Structured output

14/15

Math

10/15

Multilingual

9/10

Category levels

Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.6
Model format: GGUF
Hardware profile: HIGH-END
Result hash: b6cbae89e81a0c3321ee2fd5c40ebbb45fbdfe2c2b302ac17a466d18a0239b54

Interpretation

Hardware fit: 90/100. Overall suitability: EXCELLENT (Global 82/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Bench Environment

CPU load: avg 19% (peak 21%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest