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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

gemma3:1b

OLLAMA GGUF

gemma3 · 999.89M · Q4_K_M

Good

Feb 28, 2026 · Apple M4

Global Score

36 vs 68

Hardware Fit

53 vs 98

Quality Score

28 vs 55

Hardware

deepseek-r1-distil… gemma3:1b

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

deepseek-r1-distil… gemma3:1b

Tokens/sec10.339.4

First chunk27 msN/A

TTFT20.7 s362 ms

Load time15.4 s0.3 s

Memory usage1.0 GB1.3 GB

Memory %4%4%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

gemma3:1b

Speed

40/50

TTFT

30/20

Memory

28/30

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

gemma3:1b

Reasoning

6/20

Coding

13/20

Instruction

15/20

Structured

12/15

Math

1/15

Multilingual

8/10

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

View deepseek-r1-distil… details | View gemma3:1b 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