phi4-mini:latest

phi3 · 3.8B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

nous-hermes2:latest

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

75 vs 71

Hardware Fit

100 vs 87

Quality Score

58 vs 60

Hardware

phi4-mini:latest nous-hermes2:latest

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

phi4-mini:latest nous-hermes2:latest

Tokens/sec36.215.9

TTFT190 ms345 ms

Load time0.8 s0.4 s

Memory usage8.3 GB6.6 GB

Memory %26%21%

HW Fit Score Breakdown

phi4-mini:latest

Speed

40/40

TTFT

30/30

Memory

30/30

nous-hermes2:latest

Speed

27/40

TTFT

30/30

Memory

30/30

Quality

phi4-mini:latest

Reasoning

12/20

Coding

10/20

Instruction

10/20

Structured

11/15

Math

5/15

Multilingual

10/10

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

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

View phi4-mini:latest details | View nous-hermes2:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running