phi3:3.8b

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

llama2:7b

llama · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

64 vs 55

Hardware Fit

100 vs 99

Quality Score

48 vs 36

Hardware

phi3:3.8b llama2:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

phi3:3.8b llama2:7b

Tokens/sec42.025.1

TTFT142 ms228 ms

Load time1.1 s0.4 s

Memory usage16.0 GB5.8 GB

Memory %50%18%

HW Fit Score Breakdown

phi3:3.8b

Speed

40/40

TTFT

30/30

Memory

30/30

llama2:7b

Speed

39/40

TTFT

30/30

Memory

30/30

Quality

phi3:3.8b

Reasoning

12/20

Coding

3/20

Instruction

11/20

Structured

10/15

Math

5/15

Multilingual

7/10

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

llama2:7b

Reasoning

4/20

Coding

3/20

Instruction

13/20

Structured

8/15

Math

1/15

Multilingual

7/10

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

View phi3:3.8b details | View llama2:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running