gemma-4-26b-a4b-it@iq3_xxs

gemma4 · 26B · IQ3_XXS

Docker Container (Intel Gen Intel® Core™ i9-11900H)

15 GB · Ubuntu 26.04 LTS

Tested on June 29, 2026

Top 17% Compare

Global Score

83 /100

Excellent

Hardware Fit

58/100

Quality

94/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Docker Container
CPU: Intel Gen Intel® Core™ i9-11900H
Cores: 16 threads (8 cores)
Frequency: 2.5 GHz
RAM: 15 GB
GPU: TigerLake-H GT1 [UHD Graphics]
OS: Ubuntu 26.04 LTS
Arch: x64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 10.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.5
First chunk latency Delay before the first streamed chunk arrives from runtime: 8 ms
Time to first token How fast the model starts responding — lower is better: 3.5 s
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: 6.4 GB (41%)
Total tokens Total number of tokens generated across all benchmark prompts: 1436

Score breakdown

Speed

19/50

Time to first token

12/20

Memory

27/30

Quality

Reasoning

18/20

Coding

19/20

Instruction following

19/20

Structured output

15/15

Math

14/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.16+1
Model format: GGUF
Hardware profile: BALANCED
Result hash: bfa431799609b07833874748d1ad8bded0f9c614996e5148b3d9f35159099f8e

Interpretation

Hardware fit: 58/100. Overall suitability: EXCELLENT (Global 83/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Significant swap activity during benchmark (+0.8 GB). Model may exceed available RAM — results are severely degraded.

Bench Environment

Thermal: nominal Swap delta: +0.8 GB CPU load: avg 53% (peak 55%)

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