llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

phi4-mini

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

64 vs 39

Hardware Fit

56 vs 66

Quality Score

70 vs 21

Hardware

llama3.1:8b phi4-mini

MachineMac MiniMacBook Air

CPUApple M4 ProApple M4

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.7.4macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

llama3.1:8b phi4-mini

Tokens/sec5.521.8

TTFT1.4 s9.6 s

Load time3.7 s3.5 s

Memory usage28.6 GB0.0 GB

Memory %45%0%

HW Fit Score Breakdown

llama3.1:8b

Speed

5/40

TTFT

22/30

Memory

29/30

phi4-mini

Speed

31/40

TTFT

5/30

Memory

30/30

Quality

llama3.1:8b

Reasoning

12/20

Coding

17/20

Instruction

14/20

Structured

13/15

Math

4/15

Multilingual

10/10

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

phi4-mini

Reasoning

11/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

5/15

Multilingual

5/10

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

View llama3.1:8b details | View phi4-mini details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running