gemma-3-27b-it-qat
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 5, 2026 · Apple M4 Pro
unsloth-phi-4
LM-STUDIO MLXllama · 4bit
Mar 6, 2026 · Apple M4 Pro
Global Score
76 vs 82
Hardware Fit
51 vs 88
Quality Score
87 vs 80
Hardware
gemma-3-27b-it-qat unsloth-phi-4
MachineMac miniMac mini
CPUApple M4 ProApple M4 Pro
Cores1414
RAM64 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma-3-27b-it-qat unsloth-phi-4
Tokens/sec8.927.4
First chunk3976 ms457 ms
TTFT4.0 s457 ms
Load timeN/AN/A
Memory usage15.7 GB7.7 GB
Memory %25%12%
HW Fit Score Breakdown
gemma-3-27b-it-qat
Speed
12/50
TTFT
9/20
Memory
30/30
unsloth-phi-4
Speed
38/50
TTFT
20/20
Memory
30/30
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
unsloth-phi-4
Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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