qwen2.5:1.5b

qwen2 · 1.5B · Q4_K_M

Shanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB (ZHAOXIN KaiXian KX-7000 KaiXian KX-7000)

30 GB · Microsoft Windows 11 Pro 10.0.26100

Tested on June 17, 2026

Top 62% Compare

Global Score

65 /100

Good

Hardware Fit

87/100

Quality

56/100

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: Shanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPU: ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores: 8 total (8 perf)
Frequency: 3.6 GHz
RAM: 30 GB DDR5
GPU: ZX C-1190
OS: Microsoft Windows 11 Pro 10.0.26100
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 16.8
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 941 ms
Time to first token How fast the model starts responding — lower is better: 941 ms
Load time Time to load the model into memory before inference: 0.2 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: 1164

Score breakdown

Speed

37/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

8/20

Coding

10/20

Instruction following

12/20

Structured output

13/15

Math

5/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.14.3
Model format: GGUF
Hardware profile: ENTRY
Result hash: 25d45ffdb768f7a3682c9dc09e30d0a3f942f7204c87040ffa957e5d81a12c9b

Interpretation

Hardware fit: 87/100. Overall suitability: GOOD (Global 65/100). Category profile: Reasoning: Weak, Coding: Adequate, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Bench Environment

CPU load: avg 83% (peak 97%)

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