deepseek-r1-distill-qwen-14b-mlx

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

exaone-3.5-2.4b-instruct-mlx

LM-STUDIO MLX

exaone · 2.4B · 8bit

Good

Mar 4, 2026 · Apple M4

Global Score

36 vs 75

Hardware Fit

53 vs 100

Quality Score

28 vs 64

Hardware

deepseek-r1-distil… exaone-3.5-2.4b-in…

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

deepseek-r1-distil… exaone-3.5-2.4b-in…

Tokens/sec10.337.0

First chunk27 ms288 ms

TTFT20.7 s288 ms

Load time15.4 sN/A

Memory usage1.0 GB2.4 GB

Memory %4%8%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

exaone-3.5-2.4b-instruc…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

deepseek-r1-distill-qwe…

Reasoning

3/20

Coding

6/20

Instruction

6/20

Structured

3/15

Math

2/15

Multilingual

8/10

Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Strong

exaone-3.5-2.4b-instruc…

Reasoning

9/20

Coding

13/20

Instruction

15/20

Structured

14/15

Math

5/15

Multilingual

8/10

Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

View deepseek-r1-distil… details | View exaone-3.5-2.4b-in… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest