qwen3:8b

qwen3 · 8.2B · Q4_K_M

THINKING MODEL

ASUS (Intel Core™ Ultra 9 285K)

47 GB · Microsoft Windows 11 Pro 10.0.26200

Tested on March 5, 2026 · Submitted by abayaz61

Top 8% Compare

Global Score

84 /100

Excellent

Hardware Fit

97/100

Quality

79/100

Get this model

🦙

Ollama

ollama pull qwen3:8b

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: ASUS
CPU: Intel Core™ Ultra 9 285K
Cores: 24 total (24 perf)
Frequency: 3.7 GHz
RAM: 47 GB DDR5
GPU: NVIDIA GeForce RTX 5090, Intel(R) Graphics
OS: Microsoft Windows 11 Pro 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 208.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±2.8
First chunk latency Delay before the first streamed chunk arrives from runtime: 82 ms
Time to first token How fast the model starts responding — lower is better: 1.3 s
Load time Time to load the model into memory before inference: 1.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 9.6 GB (20%)
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: ~966

Score breakdown

Speed

50/50

Time to first token

18/20

Memory

29/30

Quality

Reasoning

18/20

Coding

10/20

Instruction following

14/20

Structured output

15/15

Math

12/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.6
Model format: GGUF
Hardware profile: HIGH-END
Result hash: a745c4fac0621b909ef8306d5424d5fdda9ff5a1b9d23d7fb1458ed5d8d8ba0b

Interpretation

Hardware fit: 97/100. Overall suitability: EXCELLENT (Global 84/100). Category profile: Reasoning: Strong, Coding: Weak, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Thermal: nominal CPU load: avg 11% (peak 14%)

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