cogito:3b

OLLAMA GGUF

llama · 3.6B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

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

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

Global Score

67 vs 36

Hardware Fit

100 vs 53

Quality Score

53 vs 28

Hardware

cogito:3b deepseek-r1-distil…

MachineMacBook AirMac mini

CPUApple M4Apple M4

Cores1010

RAM32 GB24 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

cogito:3b deepseek-r1-distil…

Tokens/sec45.610.3

First chunk177 ms27 ms

TTFT177 ms20.7 s

Load time0.8 s15.4 s

Memory usage7.0 GB1.0 GB

Memory %22%4%

HW Fit Score Breakdown

cogito:3b

Speed

50/50

TTFT

20/20

Memory

30/30

deepseek-r1-distill-qwe…

Speed

23/50

TTFT

0/20

Memory

30/30

Quality

cogito:3b

Reasoning

6/20

Coding

8/20

Instruction

13/20

Structured

15/15

Math

2/15

Multilingual

9/10

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

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

View cogito:3b details | View deepseek-r1-distil… 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