deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

orca-mini:3b

llama · 3B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score

25 vs 54

Hardware Fit

46 vs 100

Quality Score

11 vs 24

Hardware

deepseek-r1:14b orca-mini:3b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

deepseek-r1:14b orca-mini:3b

Tokens/sec10.830.6

TTFT30.0 s126 ms

Load time5.3 s0.4 s

Memory usage16.5 GB2.6 GB

Memory %52%8%

HW Fit Score Breakdown

deepseek-r1:14b

Speed

16/40

TTFT

0/30

Memory

30/30

orca-mini:3b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

deepseek-r1:14b

Reasoning

1/20

Coding

0/20

Instruction

2/20

Structured

1/15

Math

1/15

Multilingual

6/10

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

orca-mini:3b

Reasoning

2/20

Coding

2/20

Instruction

13/20

Structured

3/15

Math

1/15

Multilingual

3/10

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

View deepseek-r1:14b details | View orca-mini:3b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running