deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

llama3.1:8b

llama · 8.0B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

25 vs 77

Hardware Fit

46 vs 93

Quality Score

11 vs 67

Hardware

deepseek-r1:14b llama3.1:8b

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 llama3.1:8b

Tokens/sec10.820.3

TTFT30.0 s315 ms

Load time5.3 s1.1 s

Memory usage16.5 GB10.4 GB

Memory %52%33%

HW Fit Score Breakdown

deepseek-r1:14b

Speed

16/40

TTFT

0/30

Memory

30/30

llama3.1:8b

Speed

33/40

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

llama3.1:8b

Reasoning

12/20

Coding

15/20

Instruction

13/20

Structured

13/15

Math

4/15

Multilingual

10/10

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

View deepseek-r1:14b details | View llama3.1:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running