gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
76 vs 50
Hardware Fit
51 vs 97
Quality Score
87 vs 30
Hardware
gemma-3-27b-it-qat gemma3:270m
MachineMac miniMacBook Pro
CPUApple M4 ProApple M3 Pro
Cores1412
RAM64 GB36 GB
GPUApple M4 ProApple M3 Pro
OSmacOS 15.7.4macOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma-3-27b-it-qat gemma3:270m
Tokens/sec8.9239.2
First chunk3976 ms127 ms
TTFT4.0 s127 ms
Load timeN/A0.7 s
Memory usage15.7 GB0.6 GB
Memory %25%2%
HW Fit Score Breakdown
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
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
gemma3:270m
Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
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