mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
maternion/ling-3.0-tiny:8b
OLLAMA GGUFbailingmoe3 · 7.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
80 vs 88
Hardware Fit
100 vs 98
Quality Score
71 vs 83
Hardware
mlx-community/gemm… maternion/ling-3.0…
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/gemm… maternion/ling-3.0…
Tokens/sec43.273.0
First chunk428 ms175 ms
TTFT428 ms175 ms
Load timeN/A3.2 s
Memory usage1.3 GB5.9 GB
Memory %4%37%
HW Fit Score Breakdown
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
maternion/ling-3.0-tiny…
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
maternion/ling-3.0-tiny…
Reasoning
16/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
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