qwen3:32b

OLLAMA GGUF

qwen3 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

bloomz-560m

LM-STUDIO GGUF

bloom · 560M · Q4_K_M

Not Rec.

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score

79 vs 30

Hardware Fit

59 vs 85

Quality Score

88 vs 7

Hardware

qwen3:32b bloomz-560m

MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20BUS00700

CPUCortex-X925Intel Core™ i5-5300U

Cores204

RAM122 GB16 GB

GPUDevice 2e12Intel(R) HD Graphics 5500

OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045

Archarm64x64

Power Modeperformancebalanced

Performance

qwen3:32b bloomz-560m

Tokens/sec9.712.2

First chunk324 ms1167 ms

TTFT324 ms1.2 s

Load time24.5 sN/A

Memory usage26.8 GB0.5 GB

Memory %22%3%

HW Fit Score Breakdown

qwen3:32b

Speed

9/50

TTFT

20/20

Memory

30/30

bloomz-560m

Speed

38/50

TTFT

20/20

Memory

27/30

Quality

qwen3:32b

Reasoning

19/20

Coding

18/20

Instruction

15/20

Structured

15/15

Math

11/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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 qwen3:32b 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