unsloth/gemma-4-26b-a4b-it

gemma4 · 26B · Q3_K_M

Mac mini (Apple M4)

24 GB · macOS 26.3

Tested on April 5, 2026 · Submitted by cryptoepops

Top 11% Compare

Global Score

84 /100

Excellent

Hardware Fit

64/100

Quality

92/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Mac mini
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 24 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 16.5
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 32 ms
Time to first token How fast the model starts responding — lower is better: 2.2 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 19.3 GB (80%)
Total tokens Total number of tokens generated across all benchmark prompts: 1420

Score breakdown

Speed

36/50

Time to first token

18/20

Memory

10/30

Quality

Reasoning

18/20

Coding

19/20

Instruction following

17/20

Structured output

14/15

Math

14/15

Multilingual

10/10

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 0.4.9+1
Model format: GGUF
Hardware profile: ENTRY
Result hash: b1af3ee782dbbf42306b17cbf443af0710e467d6ac535f1f8c92d05a1b8f55c1

Interpretation

Hardware fit: 64/100. Overall suitability: EXCELLENT (Global 84/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Bench Environment

Power: AC Swap delta: +0.2 GB CPU load: avg 52% (peak 65%)

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