qwen2.5:1.5b

qwen2 · 1.5B · Q4_K_M

iMac (Intel Core™ i7-4771)

32 GB · macOS 15.7.3

Tested on March 16, 2026 · Submitted by Topaz750

Top 55% Compare

Global Score

65 /100

Good

Hardware Fit

92/100

Quality

54/100

Get this model

🦙

Ollama

ollama pull qwen2.5:1.5b

View on Ollama Library

ollama.com/library/qwen2.5

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: iMac
CPU: Intel Core™ i7-4771
Cores: 8 total (8 perf)
Frequency: 3.5 GHz
RAM: 32 GB DDR3
GPU: NVIDIA GeForce GTX 780M
OS: macOS 15.7.3
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 19.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 690 ms
Time to first token How fast the model starts responding — lower is better: 690 ms
Load time Time to load the model into memory before inference: 21.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 1.0 GB (3%)
Total tokens Total number of tokens generated across all benchmark prompts: 1191

Score breakdown

Speed

42/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

8/20

Coding

9/20

Instruction following

12/20

Structured output

13/15

Math

5/15

Multilingual

7/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.18.0
Model format: GGUF
Hardware profile: ENTRY
Result hash: cee47fbf6d51af85639f632a9c57a3df2d30397fddc8ef393e2acea3d6684915

Interpretation

Hardware fit: 92/100. Overall suitability: GOOD (Global 65/100). Category profile: Reasoning: Weak, Coding: Weak, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Adequate.

Bench Environment

Thermal: nominal Power: AC CPU load: avg 58% (peak 69%)

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