mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3:30b-a3b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 25, 2026 · Cortex-X925
Global Score
53 vs 84
Hardware Fit
99 vs 93
Quality Score
33 vs 80
Hardware
mlx-community/Nanb… qwen3:30b-a3b
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
mlx-community/Nanb… qwen3:30b-a3b
Tokens/sec25.492.7
First chunk266 ms286 ms
TTFT266 ms1.5 s
Load timeN/A15.3 s
Memory usage0.0 GB20.3 GB
Memory %0%17%
HW Fit Score Breakdown
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
Memory
30/30
qwen3:30b-a3b
Speed
50/50
TTFT
13/20
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
qwen3:30b-a3b
Reasoning
16/20
Coding
10/20
Instruction
18/20
Structured
13/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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