mlx-community/Llama-3.2-1B-Instruct-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
57 vs 66
Hardware Fit
100 vs 100
Quality Score
39 vs 51
Hardware
mlx-community/Llam… deepseek-r1:1.5b
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… deepseek-r1:1.5b
Tokens/sec126.485.4
First chunk139 ms115 ms
TTFT139 ms115 ms
Load timeN/A0.5 s
Memory usage0.3 GB2.6 GB
Memory %1%8%
HW Fit Score Breakdown
mlx-community/Llama-3.2…
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:1.5b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
mlx-community/Llama-3.2…
Reasoning
5/20
Coding
3/20
Instruction
15/20
Structured
10/15
Math
1/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Adequate Math: Poor Multilingual: Adequate
deepseek-r1:1.5b
Reasoning
14/20
Coding
4/20
Instruction
8/20
Structured
6/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
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