phi3:3.8b

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

codellama:7b

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

64 vs 63

Hardware Fit

100 vs 97

Quality Score

48 vs 49

Hardware

phi3:3.8b codellama: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 codellama:7b

Tokens/sec42.023.6

TTFT142 ms297 ms

Load time1.1 s0.9 s

Memory usage16.0 GB12.6 GB

Memory %50%39%

HW Fit Score Breakdown

phi3:3.8b

Speed

40/40

TTFT

30/30

Memory

30/30

codellama:7b

Speed

37/40

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

codellama:7b

Reasoning

6/20

Coding

7/20

Instruction

12/20

Structured

13/15

Math

3/15

Multilingual

8/10

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

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

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running