google/gemma-3-27b

gemma3 · 27B · 4bit

Mac mini (Apple M4)

24 GB · macOS 26.3

Tested on March 19, 2026 · Submitted by cryptoepops

Top 43% Compare

Global Score

71 /100

Not Rec.

Hardware Fit

35/100

Quality

86/100

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: 5.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 19 ms
Time to first token How fast the model starts responding — lower is better: 1.8 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: 22.0 GB (92%)
Total tokens Total number of tokens generated across all benchmark prompts: 1081

Score breakdown

Speed

12/50

Time to first token

19/20

Memory

4/30

Quality

Reasoning

16/20

Coding

18/20

Instruction following

16/20

Structured output

15/15

Math

11/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.7+4
Model format: MLX
Hardware profile: ENTRY
Result hash: 50d05eb2c240d030bdb55afe9b05f088874a50d4825b4544b3c0eec87bae4d02

Interpretation

Hardware fit: 35/100. Overall suitability: NOT RECOMMENDED (Global 71/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Warnings

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

Disqualifiers

Memory usage critical: model delta +92%

Bench Environment

Power: AC Swap delta: +0.0 GB CPU load: avg 15% (peak 17%)

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