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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

nemotron-3-super:latest

OLLAMA GGUF

nemotron_h_moe · 123.6B · Q4_K_M

Good

Oct 3, 2026 · Cortex-X925

Global Score

36 vs 74

Hardware Fit

53 vs 50

Quality Score

28 vs 84

Hardware

deepseek-r1-distil… nemotron-3-super:l…

MachineMac miniNVIDIA NVIDIA_DGX_Spark

CPUApple M4Cortex-X925

Cores1020

RAM24 GB122 GB

GPUApple M4Device 2e12

OSmacOS 26.3Ubuntu 24.04.5 LTS

Archarm64arm64

Power Modebalancedperformance

Performance

deepseek-r1-distil… nemotron-3-super:l…

Tokens/sec10.321.8

First chunk27 ms420 ms

TTFT20.7 s2.2 s

Load time15.4 s12.4 s

Memory usage1.0 GB79.5 GB

Memory %4%65%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

nemotron-3-super:latest

Speed

23/50

TTFT

10/20

Memory

17/30

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

nemotron-3-super:latest

Reasoning

17/20

Coding

18/20

Instruction

11/20

Structured

14/15

Math

14/15

Multilingual

10/10

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

View deepseek-r1-distil… details | View nemotron-3-super:l… 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