gemma-3-27b-it-qat

gemma3 · 27B · 4bit

Mac mini (Apple M4 Pro)

64 GB · macOS 15.7.4

Tested on March 5, 2026

Top 29% Compare

Global Score

76 /100

Good

Hardware Fit

51/100

Quality

87/100

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 Pro
Cores: 14 total (10 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 64 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.7.4
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 8.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±6.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 4.0 s
Time to first token How fast the model starts responding — lower is better: 4.0 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: 15.7 GB (25%)
Total tokens Total number of tokens generated across all benchmark prompts: 715

Score breakdown

Speed

12/50

Time to first token

9/20

Memory

30/30

Quality

Reasoning

16/20

Coding

18/20

Instruction following

17/20

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 0.4.6+1
Model format: MLX
Hardware profile: HIGH-END
Result hash: 91226182637feb18abc24f9c0dc5ab95806c01024b4f02bce64d6db1c8b89a35

Interpretation

Hardware fit: 51/100. Overall suitability: GOOD (Global 76/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Warnings

Token speed is unstable (stddev 6.4 tok/s, mean 8.9 tok/s) — may indicate thermal throttling or memory pressure.

Bench Environment

Power: AC CPU load: avg 25% (peak 28%)

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