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 )

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jun 26, 2026 · Cortex-X925

Global Score
91 vs 93
Hardware Fit
98 vs 87
Quality Score
88 vs 95

Hardware

Qwen3-30B:30b gpt-oss:20b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLNVIDIA NVIDIA_DGX_Spark
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Cortex-X925
Cores2020
RAM55 GB122 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.28000Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

Qwen3-30B:30b gpt-oss:20b
Tokens/sec80.560.5
First chunk158 ms527 ms
TTFT158 ms3.1 s
Load time21.8 s14.0 s
Memory usage20.3 GB12.0 GB
Memory %37%10%

HW Fit Score Breakdown

Qwen3-30B:30b

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

gpt-oss:20b

Speed
50/50
TTFT
7/20
Memory
30/30

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

gpt-oss:20b

Reasoning
19/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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