granite3.1-dense:8b

granite · 8.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

llama3:latest

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

76 vs 74

Hardware Fit

91 vs 95

Quality Score

66 vs 60

Hardware

granite3.1-dense:8b llama3:latest

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

granite3.1-dense:8b llama3:latest

Tokens/sec18.822.3

TTFT308 ms295 ms

Load time0.6 s0.8 s

Memory usage13.0 GB5.6 GB

Memory %41%18%

HW Fit Score Breakdown

granite3.1-dense:8b

Speed

31/40

TTFT

30/30

Memory

30/30

llama3:latest

Speed

35/40

TTFT

30/30

Memory

30/30

Quality

granite3.1-dense:8b

Reasoning

12/20

Coding

11/20

Instruction

15/20

Structured

14/15

Math

5/15

Multilingual

9/10

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

llama3:latest

Reasoning

9/20

Coding

9/20

Instruction

15/20

Structured

13/15

Math

4/15

Multilingual

10/10

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

View granite3.1-dense:8b details | View llama3:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running