tinyllama:1.1b

llama · 1B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

51 vs 72

Hardware Fit

100 vs 100

Quality Score

19 vs 54

Hardware

tinyllama:1.1b granite3.1-dense:2b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

tinyllama:1.1b granite3.1-dense:2b

Tokens/sec121.054.6

TTFT82 ms121 ms

Load time0.4 s0.4 s

Memory usage0.7 GB5.6 GB

Memory %2%18%

HW Fit Score Breakdown

tinyllama:1.1b

Speed

40/40

TTFT

30/30

Memory

30/30

granite3.1-dense:2b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

tinyllama:1.1b

Reasoning

2/20

Coding

1/20

Instruction

6/20

Structured

7/15

Math

0/15

Multilingual

3/10

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

granite3.1-dense:2b

Reasoning

8/20

Coding

9/20

Instruction

13/20

Structured

14/15

Math

3/15

Multilingual

7/10

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

View tinyllama:1.1b details | View granite3.1-dense:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running