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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

text-embedding-nomic-embed-text-v1.5

LM-STUDIO GGUF

nomic-bert · Q4_K_M

Marginal

Mar 3, 2026 · Apple M4

Global Score

36 vs 59

Hardware Fit

53 vs 94

Quality Score

28 vs 44

Hardware

deepseek-r1-distil… text-embedding-nom…

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… text-embedding-nom…

Tokens/sec10.345.3

First chunk27 ms2440 ms

TTFT20.7 s2.4 s

Load time15.4 sN/A

Memory usage1.0 GB0.0 GB

Memory %4%0%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

text-embedding-nomic-em…

Speed

40/50

TTFT

25/20

Memory

29/30

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

text-embedding-nomic-em…

Reasoning

10/20

Coding

3/20

Instruction

11/20

Structured

12/15

Math

3/15

Multilingual

5/10

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

View deepseek-r1-distil… details | View text-embedding-nom… 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