gemma-3-270m-it-qat-mlx
LM-STUDIO MLXgemma3_text · 270M · 4bit
Mar 4, 2026 · Apple M4
llama2:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
43 vs 56
Hardware Fit
99 vs 84
Quality Score
19 vs 44
Hardware
gemma-3-270m-it-qa… llama2:13b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma-3-270m-it-qa… llama2:13b
Tokens/sec344.213.5
First chunk173 msN/A
TTFT173 ms415 ms
Load timeN/A0.6 s
Memory usage0.3 GB10.3 GB
Memory %1%32%
HW Fit Score Breakdown
gemma-3-270m-it-qat-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
llama2:13b
Speed
24/50
TTFT
30/20
Memory
30/30
Quality
gemma-3-270m-it-qat-mlx
Reasoning
4/20
Coding
0/20
Instruction
9/20
Structured
3/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
llama2:13b
Reasoning
9/20
Coding
3/20
Instruction
13/20
Structured
7/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor 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