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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score

36 vs 77

Hardware Fit

53 vs 90

Quality Score

28 vs 71

Hardware

deepseek-r1-distil… spark-x2.5-4b

MachineMac miniASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM

CPUApple M4AMD Ryzen 7 4800H

Cores1016

RAM24 GB15 GB

GPUApple M4AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU

OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

deepseek-r1-distil… spark-x2.5-4b

Tokens/sec10.348.9

First chunk27 ms20 ms

TTFT20.7 s168 ms

Load time15.4 sN/A

Memory usage1.0 GB9.4 GB

Memory %4%61%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

spark-x2.5-4b

Speed

50/50

TTFT

20/20

Memory

20/30

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

spark-x2.5-4b

Reasoning

13/20

Coding

14/20

Instruction

16/20

Structured

15/15

Math

4/15

Multilingual

9/10

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

View deepseek-r1-distil… details | View spark-x2.5-4b 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