GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-4620 0
Global Score
79 vs 71
Hardware Fit
59 vs 42
Quality Score
88 vs 84
Hardware
GPT-20B:20b qwen3:30b-a3b-inst…
MachineGMKtec NucBox EVO-T2SDell Inc. PowerEdge R820
CPUIntel Core™ Ultra X7 358HIntel Xeon® E5-4620 0
Cores1664
RAM64 GB256 GB
GPUIntel(R) Arc(TM) B390 GPUMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced
Performance
GPT-20B:20b qwen3:30b-a3b-inst…
Tokens/sec19.34.0
First chunk2004 ms2070 ms
TTFT10.4 s2.1 s
Load time10.4 s44.5 s
Memory usage12.9 GB17.7 GB
Memory %20%7%
HW Fit Score Breakdown
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
qwen3:30b-a3b-instruct-…
Speed
3/50
TTFT
9/20
Memory
30/30
Quality
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:30b-a3b-instruct-…
Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
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