phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

llama2:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

28 vs 56

Hardware Fit

66 vs 84

Quality Score

11 vs 44

Hardware

phi-1_5 llama2:13b

MachineLENOVO 20BUS00700MacBook Air

CPUIntel Core™ i5-5300UApple M4

Cores410

RAM16 GB32 GB

GPUIntel(R) HD Graphics 5500Apple M4

OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

phi-1_5 llama2:13b

Tokens/sec6.913.5

First chunk3040 msN/A

TTFT3.0 s415 ms

Load timeN/A0.6 s

Memory usage1.4 GB10.3 GB

Memory %9%32%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

llama2:13b

Speed

24/50

TTFT

30/20

Memory

30/30

Quality

phi-1_5

Reasoning

2/20

Coding

2/20

Instruction

3/20

Structured

0/15

Math

2/15

Multilingual

2/10

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

llama2:13b

Reasoning

9/20

Coding

3/20

Instruction

13/20

Structured

7/15

Math

3/15

Multilingual

9/10

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

View phi-1_5 details | View llama2:13b details

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