phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5:2b

OLLAMA GGUF

qwen35 · 2.3B · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score

28 vs 13

Hardware Fit

66 vs 41

Quality Score

11 vs 1

Hardware

phi-1_5 qwen3.5:2b

MachineLENOVO 20BUS00700LENOVO 20L7CTO1WW

CPUIntel Core™ i5-5300UIntel Core™ i5-8350U

Cores48

RAM16 GB23 GB

GPUIntel(R) HD Graphics 5500Kaby Lake-R GT2 [UHD Graphics 620]

OSMicrosoft Windows 10 Professionnel 10.0.19045Fedora Linux 43

Archx64x64

Power Modebalancedlow-power

Performance

phi-1_5 qwen3.5:2b

Tokens/sec6.94.5

First chunk3040 ms1413 ms

TTFT3.0 s31.1 s

Load timeN/A7.1 s

Memory usage1.4 GB3.8 GB

Memory %9%16%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

qwen3.5:2b

Speed

11/50

TTFT

0/20

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

qwen3.5:2b

Reasoning

0/20

Coding

0/20

Instruction

1/20

Structured

0/15

Math

0/15

Multilingual

0/10

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

View phi-1_5 details | View qwen3.5:2b 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