mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
smollm2:360m
OLLAMA GGUFllama · 361.82M · F16
Mar 2, 2026 · Apple M4
Global Score
53 vs 52
Hardware Fit
99 vs 100
Quality Score
33 vs 32
Hardware
mlx-community/Nanb… smollm2:360m
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/Nanb… smollm2:360m
Tokens/sec25.4117.9
First chunk266 msN/A
TTFT266 ms43 ms
Load timeN/A0.4 s
Memory usage0.0 GB1.2 GB
Memory %0%4%
HW Fit Score Breakdown
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
Memory
30/30
smollm2:360m
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
mlx-community/Nanbeige4…
Reasoning
10/20
Coding
7/20
Instruction
1/20
Structured
1/15
Math
11/15
Multilingual
3/10
Reasoning: Adequate Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Weak
smollm2:360m
Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
9/15
Math
4/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
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