mlx-community/Llama-3.2-3B-Instruct-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
granite3.1-dense:8b
OLLAMA GGUFgranite · 8.2B · Q4_K_M
Mar 1, 2026 · Apple M4
Global Score
74 vs 74
Hardware Fit
100 vs 91
Quality Score
63 vs 66
Hardware
mlx-community/Llam… granite3.1-dense:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/Llam… granite3.1-dense:8b
Tokens/sec50.618.8
First chunk257 msN/A
TTFT257 ms308 ms
Load timeN/A0.6 s
Memory usage0.7 GB13.0 GB
Memory %2%41%
HW Fit Score Breakdown
mlx-community/Llama-3.2…
Speed
50/50
TTFT
20/20
Memory
30/30
granite3.1-dense:8b
Speed
31/50
TTFT
30/20
Memory
30/30
Quality
mlx-community/Llama-3.2…
Reasoning
9/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
granite3.1-dense:8b
Reasoning
12/20
Coding
11/20
Instruction
15/20
Structured
14/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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