mlx-community/Llama-3.2-3B-Instruct-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
74 vs 84
Hardware Fit
100 vs 69
Quality Score
63 vs 91
Hardware
mlx-community/Llam… gptoss · 20.9B · M…
MachineMacBook AirMac Pro
CPUApple M4Intel Core™ i5-10400
Cores1012
RAM32 GB32 GB
GPUApple M4AMD Radeon RX 6700 XT
OSmacOS 26.3macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
mlx-community/Llam… gptoss · 20.9B · M…
Tokens/sec50.617.5
First chunk257 ms643 ms
TTFT257 ms7.7 s
Load timeN/A0.0 s
Memory usage0.7 GB0.8 GB
Memory %2%3%
HW Fit Score Breakdown
mlx-community/Llama-3.2…
Speed
50/50
TTFT
20/20
Memory
30/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
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