nous-hermes2:latest

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

granite3.1-dense:8b

granite · 8.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

71 vs 76

Hardware Fit

87 vs 91

Quality Score

60 vs 66

Hardware

nous-hermes2:latest granite3.1-dense:8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

nous-hermes2:latest granite3.1-dense:8b

Tokens/sec15.918.8

TTFT345 ms308 ms

Load time0.4 s0.6 s

Memory usage6.6 GB13.0 GB

Memory %21%41%

HW Fit Score Breakdown

nous-hermes2:latest

Speed

27/40

TTFT

30/30

Memory

30/30

granite3.1-dense:8b

Speed

31/40

TTFT

30/30

Memory

30/30

Quality

nous-hermes2:latest

Reasoning

11/20

Coding

9/20

Instruction

12/20

Structured

15/15

Math

4/15

Multilingual

9/10

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

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

View nous-hermes2:latest details | View granite3.1-dense:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running