gemma4:e2b

gemma4 · 5.1B · Q4_K_M

ECO MODE

Dell Inc. Inspiron 15 3530 (Intel Gen Intel® Core™ i7-1355U)

31 GB · cachyos rolling

Tested on May 24, 2026

Top 46% Compare

Global Score

72 /100

Good

Hardware Fit

71/100

Quality

72/100

Get this model

🦙

Ollama

ollama pull gemma4:e2b

View on Ollama Library

ollama.com/library/gemma4

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Dell Inc. Inspiron 15 3530
CPU: Intel Gen Intel® Core™ i7-1355U
Cores: 12 total (2 perf + 8 eff)
Frequency: 2.8 GHz
RAM: 31 GB
GPU: Raptor Lake-P [Iris Xe Graphics]
OS: cachyos rolling
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 10.8
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 1.4 s
Time to first token How fast the model starts responding — lower is better: 1.4 s
Load time Time to load the model into memory before inference: 6.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 7.2 GB (23%)
Total tokens Total number of tokens generated across all benchmark prompts: 1047

Score breakdown

Speed

21/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

10/20

Coding

16/20

Instruction following

14/20

Structured output

15/15

Math

7/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.24.0
Model format: GGUF
Hardware profile: BALANCED
Result hash: 2843b93d4282a0ed0688f55a9f4dfff0114d8420f4906b0757b552b31cd38d12

Interpretation

Hardware fit: 71/100. Overall suitability: GOOD (Global 72/100). Category profile: Reasoning: Weak, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Warnings

System was in low-power mode during this benchmark.
Significant swap activity during benchmark (+1.0 GB). Model may exceed available RAM — results are severely degraded.
Running on battery power — performance may be reduced.

Bench Environment

Thermal: nominal Power: Battery Swap delta: +1.0 GB CPU load: avg 22% (peak 23%)

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