vicuna:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 1, 2026 · Apple M4
mlx-community/Nanbeige4.1-3B-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
59 vs 53
Hardware Fit
84 vs 99
Quality Score
48 vs 33
Hardware
vicuna:13b mlx-community/Nanb…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
vicuna:13b mlx-community/Nanb…
Tokens/sec13.425.4
First chunkN/A266 ms
TTFT438 ms266 ms
Load time0.6 sN/A
Memory usage10.3 GB0.0 GB
Memory %32%0%
HW Fit Score Breakdown
vicuna:13b
Speed
24/50
TTFT
30/20
Memory
30/30
mlx-community/Nanbeige4…
Speed
49/50
TTFT
20/20
Memory
30/30
Quality
vicuna:13b
Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
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
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