qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

bloomz-560m

LM-STUDIO GGUF

bloom · 560M · Q4_K_M

Not Rec.

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score

34 vs 30

Hardware Fit

58 vs 85

Quality Score

23 vs 7

Hardware

qwen3.5:latest bloomz-560m

MachineMac miniLENOVO 20BUS00700

CPUApple M4Intel Core™ i5-5300U

Cores104

RAM16 GB16 GB

GPUApple M4Intel(R) HD Graphics 5500

OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

qwen3.5:latest bloomz-560m

Tokens/sec13.312.2

First chunk438 ms1167 ms

TTFT19.8 s1.2 s

Load time0.2 sN/A

Memory usage8.0 GB0.5 GB

Memory %50%3%

HW Fit Score Breakdown

qwen3.5:latest

Speed

32/50

TTFT

1/20

Memory

25/30

bloomz-560m

Speed

38/50

TTFT

20/20

Memory

27/30

Quality

qwen3.5:latest

Reasoning

6/20

Coding

1/20

Instruction

3/20

Structured

0/15

Math

5/15

Multilingual

8/10

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

bloomz-560m

Reasoning

4/20

Coding

0/20

Instruction

2/20

Structured

0/15

Math

0/15

Multilingual

1/10

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

View qwen3.5:latest details | View bloomz-560m 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