Back to leaderboard

llama3:latest

llama · 8.0B · Q4_0

Good

Mar 1, 2026 · Apple M4

phi4-mini:latest

phi3 · 3.8B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
68 vs 75
Hardware Fit
94 vs 100
Quality Score
51 vs 58

Hardware

llama3:latest phi4-mini:latest
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

llama3:latest phi4-mini:latest
Tokens/sec21.436.2
TTFT297 ms190 ms
Load time0.8 s0.8 s
Memory usage5.6 GB8.3 GB
Memory %18%26%

HW Fit Score Breakdown

llama3:latest

Speed
34/40
TTFT
30/30
Memory
30/30

phi4-mini:latest

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

Quality

llama3:latest

Reasoning
9/20
Coding
0/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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
View llama3:latest details | View phi4-mini:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running