gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Jul 7, 2026 · Cortex-X925
openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
88 vs 84
Hardware Fit
80 vs 65
Quality Score
92 vs 92
Hardware
gemma4:26b openai/gpt-oss-20b
MachineASUSTeK COMPUTER INC. GX10ASUS
CPUCortex-X925AMD Ryzen 7 7800X3D 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archarm64x64
Power Modeperformanceperformance
Performance
gemma4:26b openai/gpt-oss-20b
Tokens/sec66.7221.5
First chunk583 ms5 ms
TTFT30.0 s30.0 s
Load time6.7 sN/A
Memory usage17.6 GB21.1 GB
Memory %15%69%
HW Fit Score Breakdown
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
15/30
Quality
gemma4:26b
Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
openai/gpt-oss-20b
Reasoning
19/20
Coding
15/20
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest