phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score

28 vs 57

Hardware Fit

66 vs 61

Quality Score

11 vs 55

Hardware

phi-1_5 qwen3.5:9b

MachineLENOVO 20BUS00700AZW GTR Pro

CPUIntel Core™ i5-5300UAMD RYZEN AI MAX+ 395

Cores432

RAM16 GB125 GB

GPUIntel(R) HD Graphics 5500AMD Radeon 8060S

OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 24.04.4 LTS

Archx64x64

Power Modebalancedlow-power

Performance

phi-1_5 qwen3.5:9b

Tokens/sec6.930.3

First chunk3040 ms205 ms

TTFT3.0 s8.7 s

Load timeN/A5.6 s

Memory usage1.4 GB18.8 GB

Memory %9%15%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

qwen3.5:9b

Speed

30/50

TTFT

1/20

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

qwen3.5:9b

Reasoning

17/20

Coding

2/20

Instruction

7/20

Structured

8/15

Math

12/15

Multilingual

9/10

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

View phi-1_5 details | View qwen3.5:9b 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