starling-lm:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 6, 2026 · Apple M4
mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
65 vs 45
Hardware Fit
96 vs 100
Quality Score
52 vs 21
Hardware
starling-lm:7b mlx-community/quan…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
starling-lm:7b mlx-community/quan…
Tokens/sec23.844.4
First chunk232 ms336 ms
TTFT232 ms336 ms
Load time0.4 sN/A
Memory usage5.3 GB0.1 GB
Memory %17%0%
HW Fit Score Breakdown
starling-lm:7b
Speed
46/50
TTFT
20/20
Memory
30/30
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
starling-lm:7b
Reasoning
10/20
Coding
13/20
Instruction
8/20
Structured
3/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Adequate Multilingual: Strong
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor
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