bloomz-560m

bloom · 560M · Q4_K_M

LENOVO 20BUS00700 (Intel Core™ i5-5300U)

16 GB · Microsoft Windows 10 Professionnel 10.0.19045

Tested on March 8, 2026

Top 97% Compare

Global Score

30 /100

Not Rec.

Hardware Fit

85/100

Quality

7/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: LENOVO 20BUS00700
CPU: Intel Core™ i5-5300U
Cores: 4 total (4 perf)
Frequency: 2.3 GHz
RAM: 16 GB DDR3
GPU: Intel(R) HD Graphics 5500
OS: Microsoft Windows 10 Professionnel 10.0.19045
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 12.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1185.9
First chunk latency Delay before the first streamed chunk arrives from runtime: 1.2 s
Time to first token How fast the model starts responding — lower is better: 1.2 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 0.5 GB (3%)
Total tokens Total number of tokens generated across all benchmark prompts: 988

Score breakdown

Speed

38/50

Time to first token

20/20

Memory

27/30

Quality

Reasoning

4/20

Coding

0/20

Instruction following

2/20

Structured output

0/15

Math

0/15

Multilingual

1/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: GGUF
Hardware profile: ENTRY
Result hash: f9b10ea9fabfb59dae677133b39063f0a1f7a265364f3585e0a659b79bbbeae2

Interpretation

Hardware fit: 85/100. Overall suitability: NOT RECOMMENDED (Global 30/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Poor, Multilingual: Poor. Warning: model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.

Warnings

Model produced very low accuracy on quality tasks — results may be unusable despite good hardware performance.
Token speed is unstable (stddev 1185.9 tok/s, mean 12.2 tok/s) — may indicate thermal throttling or memory pressure.

Bench Environment

Power: AC CPU load: avg 41% (peak 50%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest