gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
google/gemma-3-27b
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 19, 2026 · Apple M4
Global Score
76 vs 71
Hardware Fit
51 vs 35
Quality Score
87 vs 86
Hardware
gemma-3-27b-it-qat google/gemma-3-27b
MachineMac miniMac mini
CPUApple M4 ProApple M4
Cores1410
RAM64 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma-3-27b-it-qat google/gemma-3-27b
Tokens/sec8.95.9
First chunk3976 ms19 ms
TTFT4.0 s1.8 s
Load timeN/AN/A
Memory usage15.7 GB22.0 GB
Memory %25%92%
HW Fit Score Breakdown
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
google/gemma-3-27b
Speed
12/50
TTFT
19/20
Memory
4/30
Quality
gemma-3-27b-it-qat
Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
google/gemma-3-27b
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest