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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score

36 vs 62

Hardware Fit

53 vs 77

Quality Score

28 vs 55

Hardware

deepseek-r1-distil… google/gemma-4-e4b

MachineMac miniLENOVO 82JQ

CPUApple M4AMD Ryzen 7 5800H

Cores1016

RAM24 GB16 GB

GPUApple M4NVIDIA GeForce RTX 3060 Laptop GPU

OSmacOS 26.3Microsoft Windows 11 家庭版中文版 10.0.26100

Archarm64x64

Power Modebalancedbalanced

Performance

deepseek-r1-distil… google/gemma-4-e4b

Tokens/sec10.327.6

First chunk27 ms23 ms

TTFT20.7 s480 ms

Load time15.4 sN/A

Memory usage1.0 GB13.2 GB

Memory %4%83%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

google/gemma-4-e4b

Speed

48/50

TTFT

20/20

Memory

9/30

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

google/gemma-4-e4b

Reasoning

18/20

Coding

17/20

Instruction

5/20

Structured

3/15

Math

11/15

Multilingual

1/10

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

View deepseek-r1-distil… details | View google/gemma-4-e4b 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