qwen3-coder:30b

qwen3moe · 30.5B · Q4_K_M

HP HP Pavilion Laptop 15-eh1xxx (AMD Ryzen 5 5500U)

63 GB · Microsoft Windows 10 Enterprise LTSC 10.0.19044

Tested on June 18, 2026 · Submitted by Telemok

Top 21% Compare

Global Score

82 /100

Excellent

Hardware Fit

71/100

Quality

87/100

Get this model

🦙

Ollama

ollama pull qwen3-coder:30b

View on Ollama Library

ollama.com/library/qwen3-coder

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: HP HP Pavilion Laptop 15-eh1xxx
CPU: AMD Ryzen 5 5500U
Cores: 12 total (12 perf)
Frequency: 2.1 GHz
RAM: 63 GB DDR4
GPU: AMD Radeon(TM) Graphics
OS: Microsoft Windows 10 Enterprise LTSC 10.0.19044
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 14.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.5
First chunk latency Delay before the first streamed chunk arrives from runtime: 869 ms
Time to first token How fast the model starts responding — lower is better: 869 ms
Load time Time to load the model into memory before inference: 0.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 20.5 GB (32%)
Total tokens Total number of tokens generated across all benchmark prompts: 1013

Score breakdown

Speed

22/50

Time to first token

20/20

Memory

29/30

Quality

Reasoning

16/20

Coding

19/20

Instruction following

16/20

Structured output

15/15

Math

11/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.8
Model format: GGUF
Hardware profile: BALANCED
Result hash: da8ddf34110b2475662eaac11b8477aa241ee02014a5665f491e031624280766

Interpretation

Hardware fit: 71/100. Overall suitability: EXCELLENT (Global 82/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Thermal throttling detected after benchmark (critical). Results may be degraded — consider cooling or shorter runs.

Bench Environment

Thermal: critical Power: AC CPU load: avg 46% (peak 54%)

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