Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
88 vs 83
Hardware Fit
91 vs 64
Quality Score
87 vs 91
Hardware
Qwen3-30B:30b gpt-oss:120b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorCortex-X925
Cores3220
RAM31 GB122 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUDevice 2e12
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 24.04.5 LTS
Archx64arm64
Power Modebalancedperformance
Performance
Qwen3-30B:30b gpt-oss:120b
Tokens/sec42.828.6
First chunk434 ms422 ms
TTFT434 ms2.5 s
Load time19.9 s9.9 s
Memory usage17.9 GB60.1 GB
Memory %58%49%
HW Fit Score Breakdown
Qwen3-30B:30b
Speed
50/50
TTFT
20/20
Memory
21/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
Quality
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest