Back to leaderboard

phi3:3.8b

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

llama3:latest

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
69 vs 74
Hardware Fit
100 vs 95
Quality Score
48 vs 60

Hardware

phi3:3.8b llama3:latest
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 llama3:latest
Tokens/sec42.022.3
TTFT142 ms295 ms
Load time1.1 s0.8 s
Memory usage16.0 GB5.6 GB
Memory %50%18%

HW Fit Score Breakdown

phi3:3.8b

Speed
40/40
TTFT
30/30
Memory
30/30

llama3:latest

Speed
35/40
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

llama3:latest

Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View phi3:3.8b details | View llama3:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running