stablelm2:1.6b

stablelm · 2B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

phi4:14b

phi3 · 14.7B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

48 vs 65

Hardware Fit

98 vs 77

Quality Score

15 vs 57

Hardware

stablelm2:1.6b phi4:14b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

stablelm2:1.6b phi4:14b

Tokens/sec62.811.1

TTFT126 ms515 ms

Load time0.4 s9.3 s

Memory usage1.1 GB13.4 GB

Memory %3%42%

HW Fit Score Breakdown

stablelm2:1.6b

Speed

40/40

TTFT

30/30

Memory

28/30

phi4:14b

Speed

17/40

TTFT

30/30

Memory

30/30

Quality

stablelm2:1.6b

Reasoning

4/20

Coding

0/20

Instruction

6/20

Structured

1/15

Math

2/15

Multilingual

2/10

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

phi4:14b

Reasoning

16/20

Coding

0/20

Instruction

11/20

Structured

13/15

Math

7/15

Multilingual

10/10

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

View stablelm2:1.6b details | View phi4:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running