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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

aya-expanse:8b

OLLAMA GGUF

command-r · 8.0B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score

36 vs 72

Hardware Fit

53 vs 89

Quality Score

28 vs 65

Hardware

deepseek-r1-distil… aya-expanse:8b

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… aya-expanse:8b

Tokens/sec10.319.7

First chunk27 ms350 ms

TTFT20.7 s350 ms

Load time15.4 s0.9 s

Memory usage1.0 GB6.2 GB

Memory %4%20%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

aya-expanse:8b

Speed

39/50

TTFT

20/20

Memory

30/30

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

aya-expanse:8b

Reasoning

10/20

Coding

13/20

Instruction

14/20

Structured

14/15

Math

4/15

Multilingual

10/10

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

View deepseek-r1-distil… details | View aya-expanse:8b 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