mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
Global Score
53 vs 83
Hardware Fit
99 vs 65
Quality Score
33 vs 90
Hardware
mlx-community/Nanb… gpt-oss:20b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/Nanb… gpt-oss:20b
Tokens/sec25.417.1
First chunk266 ms705 ms
TTFT266 ms10.2 s
Load timeN/A23.1 s
Memory usage0.0 GB13.1 GB
Memory %0%55%
HW Fit Score Breakdown
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
Memory
30/30
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
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
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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