Back to leaderboard

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
91 vs 77
Hardware Fit
98 vs 90
Quality Score
88 vs 71

Hardware

Qwen3-30B:30b spark-x2.5-4b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 7 4800H
Cores2016
RAM55 GB15 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

Qwen3-30B:30b spark-x2.5-4b
Tokens/sec80.548.9
First chunk158 ms20 ms
TTFT158 ms168 ms
Load time21.8 sN/A
Memory usage20.3 GB9.4 GB
Memory %37%61%

HW Fit Score Breakdown

Qwen3-30B:30b

Speed
50/50
TTFT
20/20
Memory
28/30

spark-x2.5-4b

Speed
50/50
TTFT
20/20
Memory
20/30

Quality

Qwen3-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View Qwen3-30B:30b details | View spark-x2.5-4b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest