qwen3:4b

qwen3 · 4.0B · Q4_K_M

VMware, Inc. VMware Virtual Platform (Intel Core™ i7-9700)

16 GB · Ubuntu 24.04.5 LTS

Tested on November 4, 2026

Top 97% Compare

Global Score

29 /100

Not Rec.

Hardware Fit

84/100

Quality

6/100

Get this model

🦙

Ollama

ollama pull qwen3:4b

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: VMware, Inc. VMware Virtual Platform
CPU: Intel Core™ i7-9700
Cores: 4 total (4 perf)
Frequency: 3 GHz
RAM: 16 GB
GPU: Integrated / Unknown
OS: Ubuntu 24.04.5 LTS
Arch: x64

Performance

Tokens/sec Tokens generated per second — higher is better: 10.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 857 ms
Time to first token How fast the model starts responding — lower is better: 857 ms
Load time Time to load the model into memory before inference: 41.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 3.0 GB (19%)
Total tokens Total number of tokens generated across all benchmark prompts: 1317

Score breakdown

Speed

34/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

0/20

Coding

2/20

Instruction following

2/20

Structured output

0/15

Math

1/15

Multilingual

1/10

Category levels

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.40.4
Model format: GGUF
Hardware profile: ENTRY
Result hash: b9fa386fbb1162eeffbbad7c5a72970edf14fdbea813b6d1bfcfc7e8105e72cd

Interpretation

Hardware fit: 84/100. Overall suitability: NOT RECOMMENDED (Global 29/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Poor, Multilingual: Poor. Warning: model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Warnings

Model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.
CPU appears throttled (0.0 GHz current vs 3.0 GHz nominal, 0%).
High CPU load during inference (avg 98%). System may feel unresponsive — GPU-accelerated runtimes (MLX) can reduce CPU pressure.

Bench Environment

CPU load: avg 98% (peak 100%)

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