mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
Global Score
45 vs 65
Hardware Fit
100 vs 99
Quality Score
21 vs 51
Hardware
mlx-community/quan… smollm2-1.7b-instr…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/quan… smollm2-1.7b-instr…
Tokens/sec44.428.5
First chunk336 ms393 ms
TTFT336 ms393 ms
Load timeN/AN/A
Memory usage0.1 GB3.2 GB
Memory %0%10%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
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
smollm2-1.7b-instruct
Reasoning
10/20
Coding
10/20
Instruction
13/20
Structured
11/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
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