qwen3-vl:2b

qwen3vl · 2.1B · Q4_K_M

THINKING MODEL ECO MODE

AZW GTR Pro (AMD RYZEN AI MAX+ 395)

125 GB · Ubuntu 24.04.4 LTS

Tested on March 5, 2026

Top 62% Compare

Global Score

62 /100

Good

Hardware Fit

99/100

Quality

46/100

Get this model

🦙

Ollama

ollama pull qwen3-vl:2b

View on Ollama Library

ollama.com/library/qwen3-vl

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: AZW GTR Pro
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 threads (16 cores)
Frequency: 3 GHz
RAM: 125 GB
GPU: AMD Radeon 8060S
OS: Ubuntu 24.04.4 LTS
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 127.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 101 ms
Time to first token How fast the model starts responding — lower is better: 630 ms
Load time Time to load the model into memory before inference: 5.9 s
Memory usage RAM consumed during inference — percentage of total system memory: 33.2 GB (27%)
Total tokens Total number of tokens generated across all benchmark prompts: 1321
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~868

Score breakdown

Speed

50/50

Time to first token

19/20

Memory

30/30

Quality

Reasoning

7/20

Coding

0/20

Instruction following

11/20

Structured output

7/15

Math

13/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 26d3a005caeebd6dd9a2ce3afbf31da81f198900d89ec7d0b6465bb421c44313

Interpretation

Hardware fit: 99/100. Overall suitability: GOOD (Global 62/100). Category profile: Reasoning: Weak, Coding: Poor, Instruction Following: Adequate, Structured Output: Weak, Math: Strong, Multilingual: Strong.

Warnings

System was in low-power mode during this benchmark.
CPU appears throttled (2.2 GHz current vs 3.0 GHz nominal, 73%).

Bench Environment

Thermal: nominal CPU load: avg 4% (peak 4%)

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