Qwen3-Coder-30B:30B
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
88 vs 94
Hardware Fit
91 vs 91
Quality Score
87 vs 95
Hardware
Qwen3-Coder-30B:30B gpt-oss:20b
MachineGMKtec NucBox EVO-T2SFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUIntel Core™ Ultra X7 358HAMD RYZEN AI MAX+ 395
Cores1632
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro for Workstations 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
Qwen3-Coder-30B:30B gpt-oss:20b
Tokens/sec32.248.0
First chunk540 ms357 ms
TTFT540 ms2.3 s
Load time15.6 s0.2 s
Memory usage17.7 GB16.4 GB
Memory %28%26%
HW Fit Score Breakdown
Qwen3-Coder-30B:30B
Speed
41/50
TTFT
20/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
Qwen3-Coder-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:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest