Back to leaderboard

tinyllama

OLLAMA GGUF
Marginal

Mar 6, 2026 · Apple M4

phi3:14b

OLLAMA GGUF

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
43 vs 63
Hardware Fit
100 vs 83
Quality Score
19 vs 55

Hardware

tinyllama phi3:14b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

tinyllama phi3:14b
Tokens/sec133.412.7
First chunk61 msN/A
TTFT61 ms434 ms
Load time0.5 s0.9 s
Memory usage0.2 GB17.7 GB
Memory %1%55%

HW Fit Score Breakdown

tinyllama

Speed
50/50
TTFT
20/20
Memory
30/30

phi3:14b

Speed
23/50
TTFT
30/20
Memory
30/30

Quality

tinyllama

Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak

phi3:14b

Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest