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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Mar 5, 2026 · AMD Ryzen 9 8945HS

Global Score

36 vs 62

Hardware Fit

53 vs 91

Quality Score

28 vs 50

Hardware

deepseek-r1-distil… llama3.2:1b

MachineMac miniASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV

CPUApple M4AMD Ryzen 9 8945HS

Cores1016

RAM24 GB15 GB

GPUApple M4NVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics

OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

deepseek-r1-distil… llama3.2:1b

Tokens/sec10.3170.2

First chunk27 ms142 ms

TTFT20.7 s142 ms

Load time15.4 s3.2 s

Memory usage1.0 GB1.6 GB

Memory %4%11%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

llama3.2:1b

Speed

50/50

TTFT

20/20

Memory

21/30

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

llama3.2:1b

Reasoning

4/20

Coding

13/20

Instruction

14/20

Structured

13/15

Math

0/15

Multilingual

6/10

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

View deepseek-r1-distil… details | View llama3.2:1b 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