mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
Global Score
53 vs 85
Hardware Fit
99 vs 83
Quality Score
33 vs 86
Hardware
mlx-community/Nanb… Kimi-48B:48B
MachineMacBook AirHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M4Intel Core™ i7-14700F
Cores1028
RAM32 GB64 GB
GPUApple M4NVIDIA GeForce RTX 5080
OSmacOS 26.3Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
mlx-community/Nanb… Kimi-48B:48B
Tokens/sec25.432.8
First chunk266 ms724 ms
TTFT266 ms724 ms
Load timeN/A20.9 s
Memory usage0.0 GB25.8 GB
Memory %0%41%
HW Fit Score Breakdown
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
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
Kimi-48B:48B
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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