qwen3:30b-a3b

qwen3moe · 30.5B · Q4_K_M

THINKING MODEL

NVIDIA NVIDIA_DGX_Spark (Cortex-X925)

122 GB · Ubuntu 24.04.4 LTS

Tested on June 25, 2026

Top 14% Compare

Global Score

84 /100

Excellent

Hardware Fit

93/100

Quality

80/100

Get this model

🦙

Ollama

ollama pull qwen3:30b-a3b

View on Ollama Library

ollama.com/library/qwen3

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: NVIDIA NVIDIA_DGX_Spark
CPU: Cortex-X925
Cores: 20 total (20 perf)
Frequency: 3.35 GHz
RAM: 122 GB
GPU: Device 2e12
OS: Ubuntu 24.04.4 LTS
Arch: arm64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 92.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 286 ms
Time to first token How fast the model starts responding — lower is better: 1.5 s
Load time Time to load the model into memory before inference: 15.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 20.3 GB (17%)
Total tokens Total number of tokens generated across all benchmark prompts: 1348
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~736

Score breakdown

Speed

50/50

Time to first token

13/20

Memory

30/30

Quality

Reasoning

16/20

Coding

10/20

Instruction following

18/20

Structured output

13/15

Math

13/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.10
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 237c9cc7b2da7df9b216c4bbfb2942715ede26af8ef7ea28e48f730d345fe06f

Interpretation

Hardware fit: 93/100. Overall suitability: EXCELLENT (Global 84/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Thermal: nominal CPU load: avg 10% (peak 11%)

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