qwen2.5-vl:7b

qwen2vl · 7.6B · Q4_K_M

LENOVO 83DH (AMD Ryzen 7 8845HS)

15 GB · Microsoft Windows 11 Home Single Language 10.0.26300

Tested on November 8, 2026

Top 27% Compare

Global Score

84 /100

Excellent

Hardware Fit

100/100

Quality

77/100

Get this model

🦙

Ollama

ollama pull qwen2.5-vl:7b

View on Ollama Library

ollama.com/library/qwen2.5-vl

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: LENOVO 83DH
CPU: AMD Ryzen 7 8845HS
Cores: 16 total (16 perf)
Frequency: 3.8 GHz
RAM: 15 GB DDR5
GPU: NVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OS: Microsoft Windows 11 Home Single Language 10.0.26300
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 29.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 89 ms
Time to first token How fast the model starts responding — lower is better: 89 ms
Load time Time to load the model into memory before inference: 10.9 s
Memory usage RAM consumed during inference — percentage of total system memory: 4.8 GB (31%)
Total tokens Total number of tokens generated across all benchmark prompts: 1126

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

16/20

Coding

14/20

Instruction following

13/20

Structured output

15/15

Math

9/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.40.15
Model format: GGUF
Hardware profile: BALANCED
Result hash: 867956e5ac1e3ba8dfbd9183807e18c016169e09de881155d88e068b28bcca67

Interpretation

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

Warnings

Significant swap activity during benchmark (+1.1 GB). Model may exceed available RAM — results are severely degraded.
Running on battery power — performance may be reduced.

Bench Environment

Power: Battery Swap delta: +1.1 GB CPU load: avg 62% (peak 85%)

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